CA2049173C - Speech recognition apparatus - Google Patents
Speech recognition apparatusInfo
- Publication number
- CA2049173C CA2049173C CA002049173A CA2049173A CA2049173C CA 2049173 C CA2049173 C CA 2049173C CA 002049173 A CA002049173 A CA 002049173A CA 2049173 A CA2049173 A CA 2049173A CA 2049173 C CA2049173 C CA 2049173C
- Authority
- CA
- Canada
- Prior art keywords
- seat
- speech recognition
- phase
- microphones
- command
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/037—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for occupant comfort, e.g. for automatic adjustment of appliances according to personal settings, e.g. seats, mirrors, steering wheel
- B60R16/0373—Voice control
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R3/00—Circuits for transducers, loudspeakers or microphones
- H04R3/005—Circuits for transducers, loudspeakers or microphones for combining the signals of two or more microphones
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
- G10L2021/02161—Number of inputs available containing the signal or the noise to be suppressed
- G10L2021/02166—Microphone arrays; Beamforming
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2499/00—Aspects covered by H04R or H04S not otherwise provided for in their subgroups
- H04R2499/10—General applications
- H04R2499/13—Acoustic transducers and sound field adaptation in vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Otolaryngology (AREA)
- Signal Processing (AREA)
- Mechanical Engineering (AREA)
- Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)
Abstract
This invention relates to a speech recognition apparatus used in a vehicle. The speech recognition apparatus includes microphones, a speech recognition means for recognizing a voice command from the microphones, an in-phase component detecting means for detecting an in-phase component of voice signals from the microphones positioned symmetrically with respect to a driving seat, to obtain a command generated at the driving seat, a phase shift and in-phase component detecting means for detecting an in-phase component after shifting a certain amount of a voice signal phase from the microphones positioned asymmetrically with respect to passenger seats, to thereby obtain the same phase shifts and a command generated at the passenger seats, a command seat discriminating means for comparing an output level of the in-phase component detecting and the phase shift and in-phase component detecting means to discriminate at which seat a command is generated among several seats, a detecting means for detecting a validity and invalidity of commands resulting from speech obtained from outputs of the speech recognition means and command seat discriminating means to thereby control various equipment.
Also, the plurality of microphones are separated from each other to input voice commands generated at each seat in the vehicle, and the speech recognition apparatus comprises a phase shift means for shifting a predetermined amount of phases of electric signals through the microphones with the same phase shift relative to each seat, an adding means for adding output signals of the phase shift means corresponding to each seat, a maximum amplitude signal detecting means for detecting a maximum amplitude signal of output signals of each adding means as voice commands and outputting same to the speech recognition means.
Therefore, commands from the driver seat and the passenger seats are discriminated with a high reliability and the speech recognition rate in a noisy vehicle room is enhanced.
Also, the plurality of microphones are separated from each other to input voice commands generated at each seat in the vehicle, and the speech recognition apparatus comprises a phase shift means for shifting a predetermined amount of phases of electric signals through the microphones with the same phase shift relative to each seat, an adding means for adding output signals of the phase shift means corresponding to each seat, a maximum amplitude signal detecting means for detecting a maximum amplitude signal of output signals of each adding means as voice commands and outputting same to the speech recognition means.
Therefore, commands from the driver seat and the passenger seats are discriminated with a high reliability and the speech recognition rate in a noisy vehicle room is enhanced.
Description
1- 2049~7;3 SPEECH RECOGNITION APPARATUS
BACKGROUND OF THE INVENTION
l. Field of the Invention The present invention relates to a speech recognition apparatus used in a vehicle, which apparatus operates to replace manual operations normally carried out by a driver. More particularly, this invention relates to a speech recognition apparatus which discriminates commands from a drivers' seat and a passengers' seat and enhances the rate of speech recognition in a noisy vehicle room to thereby improve the reliability of the apparatus.
BACKGROUND OF THE INVENTION
l. Field of the Invention The present invention relates to a speech recognition apparatus used in a vehicle, which apparatus operates to replace manual operations normally carried out by a driver. More particularly, this invention relates to a speech recognition apparatus which discriminates commands from a drivers' seat and a passengers' seat and enhances the rate of speech recognition in a noisy vehicle room to thereby improve the reliability of the apparatus.
2. Description of the.Related Art A conventional speech recognition apparatus includes a microphone, speech recognition means for comparing an unknown speech pattern, formed by digital electrical signals converted from command voice signals from the microphone, with a registered speech pattern to recognize a speech, and various audio equipment controlled in accordance with the command recognized by the speech recognition means.
In the conventional speech recognition apparatus, when a driver at a driving seat in a vehicle gives the microphone a command of "AUDIO ON" or "AUDIO
OFF", the speech recognition means recognizes the command of "AUDIO ON" or "AUDIO OFF" and causes the various equipment to be turned ON or OFF, respectively.
Therefore, the driver does not need to let go of the steering wheel while driving, or to be forced to look away from the road while traveling, to manipulate the various audio equipment.
Also, this speech recognition apparatus also obeys similar commands from a passenger seat, (see, for example, Japanese Unexamined Patent Publication (Kokai) No. 2-77799, No. 2-184898, No. 63-56698). Nevertheless, in the above speech recognition apparatus, since, for '~
- 2 - 204~1~3 example, wipers, and rear view mirrors etc., of the vehicle can be also controlled by commands from the passenger seat, a problem arises in that such important manipulations can be performed by common~s from the passenger seat, although not desired by the driver.
Further, although an improvement in the speech recognition rate is desired in the conventional speech recognition apparatus, when used in a vehicle a problem arises in that a wide variety of noise from outside of the vehicle causes a deterioration of the speech recognition rate. To resolve the above problems, if the microphone is given a strong directivity and is thus susceptible only to voice commands from the driving seat, to thereby eliminate outside noise, the desired speech recognition cannot be performed even when there is only a slight difference in the position of the driving seat, and further, the speech recognition from the passenger seat cannot be performed at all, due to the strong directivity of the microphone.
The object of the present invention is to solve the above problems by providing a speech recognition apparatus which includes an in-phase component detecting means for detecting an in-phase component of voice 2 5 signals from microphones positioned symmetrically with respect to a driving seat, to thereby obtain a command generated at the driving seat, a phase shift and in-phase component detecting means for detecting an in-phase component after shift by a certain amount of a voice signal phase from the microphones positioned asymmetrically with respect to a passenger seat, to thereby obtain the same phase shift and a command generated at the passenger seat, a command seat discriminating means for comparing outputs levels of said in-phase component detecting means and said phase shift and in-phase component detecting means to discriminate a seat from which a command is generated _ 3 _ 204~7~
from among several seats, a determ;n;ng means for determining a validity and invalidity of commands resulting from a speech obtained from outputs of the said speech recognition means and said command seat discriminating means to thereby control various equipment. Also said plurality of microphones are positioned separately and apart from each other, to enable an input of voice commands generated at each seat in the vehicle, and are provided with a phase shift means for shifting a predetermined amount of phases of electric signals obtained through the microphones with the same phase shift relative to each seat, an adding means for adding output signals of said phase shift means corresponding to each seat, a m~ximum amplitude signal detecting means for obtaining a m~imum amplitude signal among output signals of each adding means as voice commands and outputting said signal to the speech recognition means.
With the above construction, when voice commands are generated at the driving seat, electric signals from the microphones which are in-phase are superimposed and enhanced by the in-phase component detecting means, and electric signals which are not in-phase are shifted in phase by the phase shift and in-phase component detecting means but are not enhanced. Further, when the voice commands are generated at the passenger seat, electric signals from the microphones which are not in-phase are shifted by the in-phase component detecting means but are not enhanced, and when these electric signals are in-phase, they are shifted in phase by the phase shift and in-phase component detecting means and are enhanced. Furthermore, voice commands generated at each seat which are in-phase are shifted in phase and enhanced while noisé from various directions which is not in-phase is not enhanced.
Therefore the commands generated at the microphones enable discrimination as to whether they are generated at the driving seat or at the assistant seat and enhancement from the noise with high reliability.
BRIEF DESCRIPTION OF THE DRAWINGS
The invention will be further described with reference to embodiments thereof, and to the accompanying drawings. Note, in the drawings, like parts are designated throughout by the same reference characters.
Figure l is a schematic view of a prior art speech recognition apparatus preceding the present invention;
Fig. 2A and 2B is a view of a speech recognition apparatus in accordance with a first embodiment of the present invention;
Fig. 3 is a block diagram of a speech recognition means of Fig. 2;
Fig. 4 is a circuit diagram of an in-phase component detecting means of Fig. 2;
Fig. 5 is a block diagram of a phase shift and in-phase component detecting means of Fig. 2;
Fig. 6 is a circuit diagram of a phase shift detecting means of Fig. 5;
Fig. 7 is a view showing a determination of a validity or invalidity of commands obtained from the speech recognition means;
Fig. 8 is a flowchart illustrating a consecutive operation in accordance with the first embodiment of the present invention;
Fig. 9A and 9B is a view of a speech recognition apparatus in accordance with a second embodiment of the present invention;
Fig. l0A and l0B is a view of a speech recognition apparatus in accordance with a third embodiment of the present invention;
Fig. ll is a view of a processing circuit of the phase shifting means and adding means, for processing signals from microphones provided at each - s - ~(~4~17;~
seat of Fig. 10;
Fig. 12 is a view of the phase shifting means connected to the adding means 4-1 of Fig. 11;
Fig. 13 is a view of a m~Ximum amplitude signal detecting means of Fig. 10.
DESCRIPTION OF THE PREFERRED EMBODIMENTS
Figure 1 is a schematic view of a prior art speech recognition apparatus preceding the present invention.
Referring to Fig. 1, the speech recognition apparatus comprises a microphone 1, a speech recognition means 3 for comparing an unknown speech pattern formed by digital electrical signals, converted from command voice signals from the microphone 1, with a registered speech pattern to thereby recognize a speech pattern thereof, and various audio equipment 100 controlled in accordance with the command recognized by the speech recognition means 3.
Figure 2A and 2B is a view of a speech recognition apparatus in accordance with a first embodiment of the present invention. The apparatus shown in this Figure comprises two microphones 1 for converting voice commands to electric signals, an A/D (Analog-to-Digital) converter 2 for converting analog signals from the microphones to digital signals, a speech recognition means 3 for recognizing a voice command from digital signals received from the A/D converter 2, an in-phase component detecting means 4 for detecting an in-phase component of the two microphones 1 through the A/D
converter 2 to obtain a command generated at a driving seat, a phase shift and in-phase component detecting means 5 for detecting in-phase components after shifting a certain amount of a voice signal phase from the two microphones 1 through the A/D converter to obtain the same phase shift and a command generated at a passenger seat, a command seat discriminating means 6 for comparing output levels of said in-phase component detecting means 4 and said phase shift and in-phase ~ - 6 - Z~49~73 component detecting means 5, to discriminate a seat at which a command is generated from among several seats, a determining means 7 for determining a validity or invalidity of commands resulting from speech signals obtained from the outputs of said speech recognition means 3 and said command seat discriminating means 6, various control means 8 for controlling, for example, audio equipment 100, air conditioning equipment 101, a telephone 102, navigation equipment 103, and vehicle equipment 104 such as wipers and rear view mirrors, based on the output of the determ;ning means 7, a speech synthesizing means 9 for creating artificial voice signals to thereby output control commands to the various control means 8, a D/A (Digital-to-Analog) converter 10 connected to the output terminal of the speech synthesizing means 9, a low pass filter 11 connected to the output terminal of the D/A
converter 10, for removing higher mode noise, a power amplifier 12 for driving a speaker as hereinafter described, a speaker 13 for converting electric signals to artificial voice signals obtained from the speech synthesizing means 9, a driving seat 14 in front of the speaker 13, having two microphones symmetrically positioned with respect thereto, a passenger seat 15 adjacent to the driving seat 14, and a vehicle room containing the two microphones 1, the speaker 13, the driving seat 14, and the passenger seat 15.
Further, the speech recognition means 3, the in-phase component detecting means 4, the phase shift and in-phase component detecting means 5, the command seat discriminating means 6, etc. are all part of a DSP
(Digital Signal Processor).
Next, the speech recognition means 2 is described.
Fig. 3 is a block diagram of a speech recognition means of Fig. 2. The speech recognition means 2 as shown in this Figure includes a plurality of band pass filters 30-1, 30-2, ..., 30-n each having a different 20~gl7~
band, absolute value processing means 31-1, 31-2, ....
31-n for forming electric signals from the band pass filters 30-1, 30-2, ..., 30-n into absolute values, recognition means 32 for comparing an unknown pattern having a frequency distribution obtained from the absolute value processing means 31-1, 31-2, ..., 31-n with the registered patterns, to thereby recognize a registered pattern which is most similar to the unknown pattern as a command, and memory means 33 for storing the registered patterns required by the recognition means 32. The recognition means 32 carries out the comparison of the unknown pattern and the registered pattern by successively performing a pattern matching such as a linear matching DP (Dynamic Programming). The memory means 33 stores various commands, such as audio ON/OFF, air conditioning ON/OFF, telephone ON/OFF, navigation ON/OFF, and vehicle controls, for example, wipers and rear view mirrors set/resume, as the registered patterns.
Next the in-phase component detecting means 4 is described. Figure 4 is a circuit diagram of an in-phase component detecting means of Fig. 2. The in-phase component detecting means 4 as shown in the Figure includes an adder 40 for adding electric signals from two microphones positioned symmetrically with respect to the driving seat 14, and a multiplier 41 for adjusting an output level of the adder 40. When the commands generated at the driving seat are received by each microphone 1, electric signals from each microphone 1 are in-phase, due to the positions thereof, and thus are superimposed at the adder 40. Conversely, when commands generated at the passenger seat are received by each microphone 1, electric signals from each microphone 1 are out of phase, due to the positions thereof, but are superimposed at the adder 40.
Next the phase shift and in-phase component detecting means 5 is described. Figure 5 is a block ~ - 8 - 2~ 7~
diagram of a phase shift and in-phase component detecting means of Fig. 2A and 2B. As shown in Fig. 5 the phase shift and in-phase component detecting means 5 includes phase shift means 50-1 and 50-2 for shifting the phases in the electric signals from each microphone 1, and an in-phase component detecting means 51 for defecting in-phase components of the phase shift means 50-1 and 50-2.
Next, the phase shift means 50-1 and 50-2 are described. Figure 6 is a circuit diagram of a phase shift detecting means of Fig. 5. As shown in Fig. 6 the phase shift means 50-1 (50-2) includes a plurality of unit delay devices 500-1, 500-2, 500-3, ..., 500-(n-1), 500-n for respectively delaying one sampling period through a series connection thereof, a plurality of multipliers 501-1, 501-2, 501-3, 501-4, ..., 501-(n-1), 501-n, 501-(n+l) connected to input terminals or output terminals of each unit delay devices, and a plurality of adders 502-1, 502-2, 502-3, ..., 50-2(n-2), 502(n-1), 502-n for successively adding the outputs of each of the multipliers. A multiplying coefficient of each multiplier may be adjusted to determine an amount of phase shift. Further, the construction of the in-phase component detecting means 51 is the same as that of the in-phase component detecting 4, and thus a description thereof is omitted.
At this point, two microphones 1 are positioned symmetrically with respect to the driving seat 14, and asymmetrically with respect to the passenger seat 15.
Therefore, as the commands generated at the passenger seat 15 are out of phase in the electric signals from the microphones 1, in the phase shift means 50-1 and 50-2, the multiplying coefficients of the multipliers are adjusted to be in-phase with respect to the input signals. Accordingly, a certain amount of phase from the microphones 1 is shifted and adjusted so that the in-phase component detecting means 51 of the phase shift 9 2~ .7~
and in-phase component detecting means can superimpose voice signals from the two microphones 1 with respect to the commands from the passenger seat 5, at the output level thereof.
Further, with respect to the commands generated at the passenger seat 15, the in-phase component detecting means 4 cannot cause a superimposing of the voice signals from the two microphones 1 at the output level, since each electric signal has a phase shift.
Next, the command seat discriminating means 6 is described. The command seat discriminating means 6 consists of a comparator which outputs an "H (High)"
signal when Va _ Vb, or an "L (Low)" signal when Va < Vb; where the output signals of the in-phase component detecting means 4, and the phase shift and in-phase component detecting means 5 are represented by Va and Vb respectively. When the command seat discriminating means 6 outputs an "H" signal, the command is discriminated as generated at the driving seat 14, since Va _ Vb, i.e., the output level of the electric signals passing through the in-phase component detecting means 4 is higher than that of electric signals passing through the phase shift and in-phase component detecting means.
In the reverse case, the command is discriminated as generated at the passenger seat 15.
Next, the means 7 for determ;ning the validity and invalidity of commands is described. Figure 7 is a view showing a determination of the validity and invalidity of commands resulting from a speech recognition thereof.
As shown in this Figure, the means 7 for determining the validity and invalidity of command determines the command to be valid if the command is, for example, AUDIO ON/OFF, AIR CONDITIONING ON/OFF, NAVIGATION ON/OFF
VEHICLE CONTROL SET/RESUME, which can be recognized by the speech recognition means 3, and is discriminated as generated at the driving seat 14 by the command seat discriminating means 6. Also, the means 7 determines 20~9~. ~3 the command to be valid if the command is, for example, AUDIO ON/OFF, AIR CONDITIONING ON/OFF, NAVIGATION
ON/OFF, which can be recognized by the speech recognition means 3 and is discriminated as generated at the passenger seat 15 by the command seat discriminating means 6. The means 7 determines the command to be invalid if the command is, for example, VEHICLE CONTROL
SET/RESUME, which is recognized by the speech recognition means 3 and is discriminated as generated at the passenger seat by the command seat discriminating means 6. Accordingly, a voice command from the passenger seat cannot interfere with matters which the driver should determine from a vehicle control point of view, but can be used as a command for providing various services other than the above-mentioned matters.
Next, a series of operations in accordance with the embodiment is described. Figure 8 is a flowchart illustrating a consecutive operation in accordance with the first embodiment of the present invention. As shown in this Figure, analogue electric signals of the command received through the microphones 1 are converted into digital signals (step 1). The unknown pattern formed in the digital signals of the command is then processed by the speech recognition means 3 to determine whether or not it is a registered pattern (step 2). If the unknown pattern of the commands is the same as a registered pattern, the commands are processed by the in-phase component detecting means 4 to determine whether or not they are generated at the driving seat (step 3). If the commands are generated at the driving seat, the ON/OFF
control of the corresponding audio equipment 100, air conditioning equipment 101, telephone equipment 102, and navigation equipment 103, and the vehicle set/resume control 104 is performed, through the various controlling means 8 (step 4). Further, the control content passed through the various controlling means 8 is processed to be converted to voice signals by the 2~49~73 speech synthesizing means 9, is reproduced as speech through the D/A converter 10, the low pass filter 11 and the power amplifier 12, and is broadcast at the driving seat 14 (step 5). At step 3, if the commands are determined to be from the passenger seat 15, it is determined whether the commands are vehicle control commands (step 6). If these commands are not vehicle control commands but are, for example, audio equipment ON/OFF commands, the processing and control thereof are performed at step 4. If the commands are vehicle control commands, they are not processed and controlled but are broadcast at the driving seat 14 (step 5).
Figure 9A and 9B is a view of a speech recognition apparatus in accordance with a second embodiment of the present invention. The speech recognition apparatus shown in this Figure is the same as that of the first embodiment of Fig. 2A and 2B, except that rear seats 16 and 17 are included in the vehicle room 18, a microphone 1-1 is provided at the rear seat 16 near to the driving seat 14, a phase shift and in-phase component detecting means 5-1, 5-2 and 5-3 is provided for the passenger seat 15 and the rear seats 17 and 16, respectively, and a command seat discriminating means 6-1 is provided for comparing the output level of the in-phase component detecting means 4 and the m~;mum output level of the phase shift and in-phase component detecting means 5-1, 5-2 and 5-3. The phase shift and in-phase component detecting means 5-2 adjusted to detect the same in-phase signals from the two microphones 1, taking into consideration the asymmetrical positions thereof with respect to the rear seat 17, which is different from that of the passenger seat 15. Since the microphones 1 are symmetrical with respect to the rear seat 16, to prevent the danger of an error in a command at the driving seat 14, or conversely, in a command at the rear seat 16, the phase shift and in-phase component detecting means 5-3 is - 12 - 2~49~
adjusted to detect the same in-phase signals at each of the microphones 1 and the microphone 1-1, taking into consideration the asym.metrical position thereof with respect to the rear seat 16. Therefore, when command is given from the rear seat 16, in the in-phase component detecting means 4 and the phase shift and in-phase component detecting means 5-3, the output level of the latter become too great to be discriminated from a command from the driving seat 14. In the seat discriminating means 6-1, if the output level of the in-phase component detecting means 4 is greater than that of any phase shift and in-phase component detecting means 5-1, 5-2 and 5-3, the command is discriminated as being from the driving seat 14. Conversely, if it is smaller than that of any means 5-1, 5-2 and 5-3, the command is discriminated as being from a seat other than the driving seat 14.
Figure lOA and lOB is a view of a speech recognition apparatus in accordance with a third embodiment of the present invention. The speech recognition apparatus shown in this Figure is the same as that of the second embodiment of Fig. 9A and 9B, except that microphones 1-1, 1-2, 1-3, 1-4, 1-5 and 1-6 are positioned separate from each other, and input voice commands from each seat in the vehicle room, a phase shift means 19 for shifting phases of electric signals through the microphones and A/D converter with the same phase shift relative to each seat, an adding means 20 for adding output signals of the phase shift means 19 corresponding to said each seat, and a m~ximum amplitude signal detecting means 21 for detecting the m~imum amplitude signal of output signals of each adding means 20 as the voice commands to be output to the speech recognition means 3, are provided.
Next, the phase shift means 19 and the adding means 20 are described in detail. Figure 11 shows a processing circuit of phase shifting means and adding -- - 13 - ~ O ~
means for processing signals from each microphone provided at each seat of Fig. lOA and lOB. The phase shift means 19 shown in this Figure includes phase shifters 19-1, 19-2, 19-3 and 19-4 connected to the microphone 1-1 at the corresponding above four seats through an A/D converter 2, not shown in the Figure, and phase shifters 19-5, 19-6, 19-7 and 19-8 connected to the microphone 1-2, ..., and phase shifters 19-21, 19-22, 19-23 and 19-24 connected to the microphone 1-6.
The adding means 20 includes an adder 20-1 for adding outputs of the phase shifters 19-1, 19-5, 19-9, 19-13, 19-17 and 19-21, an adder 20-2 for adding outputs of the phase shifters 19-2, 19-6, 19-10, 19-14, 19-18 and 19-22, ..., and an adder 20-4 for adding outputs of the phase shifters 19-4, 19-8, 19-12, 19-16, 19-20 and 19-24.
Figure 12 shows the phase shifting means connected to the adding means 20-1 of Fig. 11. The phase shifter 19-1 in the phase shifting means 19 shown in this Figure includes an amplifier 300 connected to the microphone 1-1, a plurality of unit delay devices 301-1, 301-2, 301-3, ..., 301-(n-1) and 301-n connected in series, for delaying one sampling period of input signal from the amplifier 100, respectively, a plurality of multipliers 302-1, 302-2, 302-3, 302-4, ... , 302-(n-1) and 302-n connected to input terminals of each of the unit delay devices, and a plurality of adders 303-1, 303-2, 303-3, ..., 303-(n-2), 303-(n-1), 303-n for successively adding outputs of each of the multipliers.
Further, the phase shifter 19-5 includes an amplifier 316 connected to the microphone 1-2, a plurality of unit delay devices 317-1, 317-2, 317-3, ..., 317-(n-1) and 317-n connected in series, for delaying one sampling period of input signal from the amplifier 316, respectively, a plurality of multipliers 318-1, 318-2, 318-3, 318-4, ..., 318-(n-1) and 318-n connected to input terminals of each of the 2~ 7~
unit delay devices, and a plurality of adders 319-1, 319-2, 319-3, ..., 319-(n-2), 319-(n-1), 319-n for successively adding outputs of each of the multipliers ... . The phase shifter 19-21 includes an amplifier 380 connected to the microphone 1-6, a plurality of unit delay devices 381-1, 381-2, 381-3, ..., 381-(n-1) 381-n connected in series, for delaying one sampling period of input signal from the amplifier 380, respectively, a plurality of multipliers 382-1, 382-2, 382-3, 382-4, ... , 382-(n-1) and 382-n connected to input ter~in~ls of each of the unit delay devices, and adders 383-1, 383-2, 383-3, ..., 383-(n-2), 383-(n-1), 383-n for successively adding outputs of each of the multipliers. Also, the adding means 20-1 is provided with an adder 400 for adding outputs of the adders 303-n, 319-n, ... , and 383-n and an amplifier 401 for amplifying the output of the adder 400. For example, when the voice command is generated at the driving seat 14 as shown in Fig. 10A, the phases of the voice command received by the microphones 1-1, 1-2, ... , 1-6 is different, and thus an adjustment of the multiplying coefficients relative to each of the multipliers corresponding to each of the phase shifters 19-1, 19-5, ..., 19-21 causes the phase shifts due to differences in the positions of the microphones to be the same as each other. Accordingly, each signal from each of the microphones in the vehicle room 18 is shifted in phase so as to be the same as each other, and is added by the adding means 20-1 and is superimposed.
On the other hand, where the noise as shown in Fig. 10A comes from the left and right directions at a right angle to the vehicle running direction, or from the front and rear relative to the vehicle running direction, each microphone is positioned so as to produce a phase shift among the microphones 1-1, 1-2 and 1-3, among the microphones 1-4, 1-5 and 1-6, between the microphones 1-1 and 1-4, between the microphones 1-2 and - 15 - Z049~73 1-5, and between the microphones 1-3 and 1-6, with respect to the above-mentioned noise. Conversely, the microphones 1-1 and 1-2 or 1-4 and 1-5 are positioned relative to each other roughly symmetrically to the left and right with respect to the voice command from the driving seat 14, and further, the microphones 1-1 and 1-4 or 1-2 and 1-5 are positioned relative to each other roughly symmetrically to the front and rear thereof, whereby the phase shift means 19 adjusts the outputs of each microphone so that they are in the same phase as each other, whereby the level of the voice command received by each of the microphones is enhanced to thus improve the S/N relative to the noise. Note, with regard to the microphones 1-3 and 1-6 positioned asymmetrically at the left and right, and which make no contribution to a reduction of the noise level, the gain of the amplifier 332 of the phase shifter 19-9 and the amplifier 380 of the phase shifter 19-21 may be made zero. Although the above explanation has been made with regard to the driving seat 14, the explanation relative to the passenger seat 15, and the rear seats 16 and 17 is the same.
Next, the mA~imum amplitude signal detecting means 21 is described. Figure 13 shows a m~Ximum amplitude signal detecting means of Fig. lOA and lOB for a speech recognition. The m~imum amplitude signal detecting means as shown in this Figure includes absolute value processed means 60-1, 60-2, 60-3 and 60-4 connected to the adding means 20-1, 20-2, 20-3 and 20-4 as shown in Fig. 13, comparators 61-1, 61-2 and 61-3 each having a noninversion terminal thereof connected to the absolute value processed means 60-1 respectively, and an inversion terminal thereof connected to each of the absolute value processed means 60-2, 60-3 and 60-4 respectively, comparators 61-4, 61-5 and 61-6 each having a non inversion terminal is connected to the absolute value processed means 60-2 respectively, and an - 16 - ~04~73 inversion terminal thereof connected to each of the absolute value processed means 60-1, 60-3 and 60-4 respectively, ..., comparators 61-10, 61-11 and 61-12 each having a non inversion term; n~l thereof connected to the absolute value processed means 60-4 respectively, and an inversion terminal thereof connected to each of the absolute value processed means 60-1, 60-2 and 60-3, AND circuits 62-1, 62-2, 62-3 and 62-4 each having an input terminal connected to the output termi n~ls of the comparators 61-1, 61-2 and 61-3, 61-4, 61-5 and 61-6, 61-7, 61-8 and 61-9, and 61-10, 61-11 and 61-12 respectively, gate circuits 63-1, 63-2, 63-3 and 63-4 for controlling each of the output signals of the adding means 20-1, 20-2, 20-3 and 20-4 by each of outputs of the AND circuits 62-1, 62-2, 62-3 and 62-4 respectively, and an OR circuit having input terminals connected to each of the output terminals of the gate circuits 63-1, 63-2, 63-3 and 63-4. With respect to the driving seat 14, the passenger seat 15, and the rear seats 16, and 17, the signals from the adding means 20-1, 20-2, 20-3 and 20-4, which are processed to be shifted in phase and added, are compared by the comparators 61-1, 61-2, ..., 61-12 through the absolute value processing means 60-1, 60-2, 60-3 and 60-4, whereby for example, when the voice commands are generated at the driving seat 14, the m~ximum amplitude signals relative to the driving seat 14 are selected by the AND circuit 62-1 to thereby control the gate circuit 63-1 corresponding to the AND circuit 62-1 and detected through the OR circuit 64. In this case, with respect to the passenger seat 15 and the rear seats 16 and 17, but not to the driving seat 14, signals which are shifted in phase and added do not include superimposed components and thus do not have a m~ximum amplitude. Accordingly, the microphones 1-1, 1-2, ... , 1-6 have a directivity relative to the driving seat 14, the passenger seat 15, and the rear seats 16 and 17 according to the positions 2~-g~
of the microphones, the phase shift means 19, the adding means 20 and the m~ximl1m amplitude signal detecting means 21.
Further, in the speech recognition apparatus in accordance with a fourth embodiment of the present invention signals can be input to the speech recognition means 3 not only from the A/D converter 2 through the center microphone 1 as in the first and the second embodiments respectively shown in the Fig. 2A and 2B, and 9A and 9B, but also from the command seat discriminating means 6, to thereby obtain a signal which is detected as a m~X; mum amplitude signal as it is, in the same way as in the third embodiment, to obtain a highly accurate speech recognition.
The present invention provides a speech recognition apparatus having a high discriminative reliability and a high recognition enhancement, due to the use of different phase shifts of signals obtained by a plurality of microphones positioned at a driving seat, a passenger seat and rear seats of the vehicle.
In the conventional speech recognition apparatus, when a driver at a driving seat in a vehicle gives the microphone a command of "AUDIO ON" or "AUDIO
OFF", the speech recognition means recognizes the command of "AUDIO ON" or "AUDIO OFF" and causes the various equipment to be turned ON or OFF, respectively.
Therefore, the driver does not need to let go of the steering wheel while driving, or to be forced to look away from the road while traveling, to manipulate the various audio equipment.
Also, this speech recognition apparatus also obeys similar commands from a passenger seat, (see, for example, Japanese Unexamined Patent Publication (Kokai) No. 2-77799, No. 2-184898, No. 63-56698). Nevertheless, in the above speech recognition apparatus, since, for '~
- 2 - 204~1~3 example, wipers, and rear view mirrors etc., of the vehicle can be also controlled by commands from the passenger seat, a problem arises in that such important manipulations can be performed by common~s from the passenger seat, although not desired by the driver.
Further, although an improvement in the speech recognition rate is desired in the conventional speech recognition apparatus, when used in a vehicle a problem arises in that a wide variety of noise from outside of the vehicle causes a deterioration of the speech recognition rate. To resolve the above problems, if the microphone is given a strong directivity and is thus susceptible only to voice commands from the driving seat, to thereby eliminate outside noise, the desired speech recognition cannot be performed even when there is only a slight difference in the position of the driving seat, and further, the speech recognition from the passenger seat cannot be performed at all, due to the strong directivity of the microphone.
The object of the present invention is to solve the above problems by providing a speech recognition apparatus which includes an in-phase component detecting means for detecting an in-phase component of voice 2 5 signals from microphones positioned symmetrically with respect to a driving seat, to thereby obtain a command generated at the driving seat, a phase shift and in-phase component detecting means for detecting an in-phase component after shift by a certain amount of a voice signal phase from the microphones positioned asymmetrically with respect to a passenger seat, to thereby obtain the same phase shift and a command generated at the passenger seat, a command seat discriminating means for comparing outputs levels of said in-phase component detecting means and said phase shift and in-phase component detecting means to discriminate a seat from which a command is generated _ 3 _ 204~7~
from among several seats, a determ;n;ng means for determining a validity and invalidity of commands resulting from a speech obtained from outputs of the said speech recognition means and said command seat discriminating means to thereby control various equipment. Also said plurality of microphones are positioned separately and apart from each other, to enable an input of voice commands generated at each seat in the vehicle, and are provided with a phase shift means for shifting a predetermined amount of phases of electric signals obtained through the microphones with the same phase shift relative to each seat, an adding means for adding output signals of said phase shift means corresponding to each seat, a m~ximum amplitude signal detecting means for obtaining a m~imum amplitude signal among output signals of each adding means as voice commands and outputting said signal to the speech recognition means.
With the above construction, when voice commands are generated at the driving seat, electric signals from the microphones which are in-phase are superimposed and enhanced by the in-phase component detecting means, and electric signals which are not in-phase are shifted in phase by the phase shift and in-phase component detecting means but are not enhanced. Further, when the voice commands are generated at the passenger seat, electric signals from the microphones which are not in-phase are shifted by the in-phase component detecting means but are not enhanced, and when these electric signals are in-phase, they are shifted in phase by the phase shift and in-phase component detecting means and are enhanced. Furthermore, voice commands generated at each seat which are in-phase are shifted in phase and enhanced while noisé from various directions which is not in-phase is not enhanced.
Therefore the commands generated at the microphones enable discrimination as to whether they are generated at the driving seat or at the assistant seat and enhancement from the noise with high reliability.
BRIEF DESCRIPTION OF THE DRAWINGS
The invention will be further described with reference to embodiments thereof, and to the accompanying drawings. Note, in the drawings, like parts are designated throughout by the same reference characters.
Figure l is a schematic view of a prior art speech recognition apparatus preceding the present invention;
Fig. 2A and 2B is a view of a speech recognition apparatus in accordance with a first embodiment of the present invention;
Fig. 3 is a block diagram of a speech recognition means of Fig. 2;
Fig. 4 is a circuit diagram of an in-phase component detecting means of Fig. 2;
Fig. 5 is a block diagram of a phase shift and in-phase component detecting means of Fig. 2;
Fig. 6 is a circuit diagram of a phase shift detecting means of Fig. 5;
Fig. 7 is a view showing a determination of a validity or invalidity of commands obtained from the speech recognition means;
Fig. 8 is a flowchart illustrating a consecutive operation in accordance with the first embodiment of the present invention;
Fig. 9A and 9B is a view of a speech recognition apparatus in accordance with a second embodiment of the present invention;
Fig. l0A and l0B is a view of a speech recognition apparatus in accordance with a third embodiment of the present invention;
Fig. ll is a view of a processing circuit of the phase shifting means and adding means, for processing signals from microphones provided at each - s - ~(~4~17;~
seat of Fig. 10;
Fig. 12 is a view of the phase shifting means connected to the adding means 4-1 of Fig. 11;
Fig. 13 is a view of a m~Ximum amplitude signal detecting means of Fig. 10.
DESCRIPTION OF THE PREFERRED EMBODIMENTS
Figure 1 is a schematic view of a prior art speech recognition apparatus preceding the present invention.
Referring to Fig. 1, the speech recognition apparatus comprises a microphone 1, a speech recognition means 3 for comparing an unknown speech pattern formed by digital electrical signals, converted from command voice signals from the microphone 1, with a registered speech pattern to thereby recognize a speech pattern thereof, and various audio equipment 100 controlled in accordance with the command recognized by the speech recognition means 3.
Figure 2A and 2B is a view of a speech recognition apparatus in accordance with a first embodiment of the present invention. The apparatus shown in this Figure comprises two microphones 1 for converting voice commands to electric signals, an A/D (Analog-to-Digital) converter 2 for converting analog signals from the microphones to digital signals, a speech recognition means 3 for recognizing a voice command from digital signals received from the A/D converter 2, an in-phase component detecting means 4 for detecting an in-phase component of the two microphones 1 through the A/D
converter 2 to obtain a command generated at a driving seat, a phase shift and in-phase component detecting means 5 for detecting in-phase components after shifting a certain amount of a voice signal phase from the two microphones 1 through the A/D converter to obtain the same phase shift and a command generated at a passenger seat, a command seat discriminating means 6 for comparing output levels of said in-phase component detecting means 4 and said phase shift and in-phase ~ - 6 - Z~49~73 component detecting means 5, to discriminate a seat at which a command is generated from among several seats, a determining means 7 for determining a validity or invalidity of commands resulting from speech signals obtained from the outputs of said speech recognition means 3 and said command seat discriminating means 6, various control means 8 for controlling, for example, audio equipment 100, air conditioning equipment 101, a telephone 102, navigation equipment 103, and vehicle equipment 104 such as wipers and rear view mirrors, based on the output of the determ;ning means 7, a speech synthesizing means 9 for creating artificial voice signals to thereby output control commands to the various control means 8, a D/A (Digital-to-Analog) converter 10 connected to the output terminal of the speech synthesizing means 9, a low pass filter 11 connected to the output terminal of the D/A
converter 10, for removing higher mode noise, a power amplifier 12 for driving a speaker as hereinafter described, a speaker 13 for converting electric signals to artificial voice signals obtained from the speech synthesizing means 9, a driving seat 14 in front of the speaker 13, having two microphones symmetrically positioned with respect thereto, a passenger seat 15 adjacent to the driving seat 14, and a vehicle room containing the two microphones 1, the speaker 13, the driving seat 14, and the passenger seat 15.
Further, the speech recognition means 3, the in-phase component detecting means 4, the phase shift and in-phase component detecting means 5, the command seat discriminating means 6, etc. are all part of a DSP
(Digital Signal Processor).
Next, the speech recognition means 2 is described.
Fig. 3 is a block diagram of a speech recognition means of Fig. 2. The speech recognition means 2 as shown in this Figure includes a plurality of band pass filters 30-1, 30-2, ..., 30-n each having a different 20~gl7~
band, absolute value processing means 31-1, 31-2, ....
31-n for forming electric signals from the band pass filters 30-1, 30-2, ..., 30-n into absolute values, recognition means 32 for comparing an unknown pattern having a frequency distribution obtained from the absolute value processing means 31-1, 31-2, ..., 31-n with the registered patterns, to thereby recognize a registered pattern which is most similar to the unknown pattern as a command, and memory means 33 for storing the registered patterns required by the recognition means 32. The recognition means 32 carries out the comparison of the unknown pattern and the registered pattern by successively performing a pattern matching such as a linear matching DP (Dynamic Programming). The memory means 33 stores various commands, such as audio ON/OFF, air conditioning ON/OFF, telephone ON/OFF, navigation ON/OFF, and vehicle controls, for example, wipers and rear view mirrors set/resume, as the registered patterns.
Next the in-phase component detecting means 4 is described. Figure 4 is a circuit diagram of an in-phase component detecting means of Fig. 2. The in-phase component detecting means 4 as shown in the Figure includes an adder 40 for adding electric signals from two microphones positioned symmetrically with respect to the driving seat 14, and a multiplier 41 for adjusting an output level of the adder 40. When the commands generated at the driving seat are received by each microphone 1, electric signals from each microphone 1 are in-phase, due to the positions thereof, and thus are superimposed at the adder 40. Conversely, when commands generated at the passenger seat are received by each microphone 1, electric signals from each microphone 1 are out of phase, due to the positions thereof, but are superimposed at the adder 40.
Next the phase shift and in-phase component detecting means 5 is described. Figure 5 is a block ~ - 8 - 2~ 7~
diagram of a phase shift and in-phase component detecting means of Fig. 2A and 2B. As shown in Fig. 5 the phase shift and in-phase component detecting means 5 includes phase shift means 50-1 and 50-2 for shifting the phases in the electric signals from each microphone 1, and an in-phase component detecting means 51 for defecting in-phase components of the phase shift means 50-1 and 50-2.
Next, the phase shift means 50-1 and 50-2 are described. Figure 6 is a circuit diagram of a phase shift detecting means of Fig. 5. As shown in Fig. 6 the phase shift means 50-1 (50-2) includes a plurality of unit delay devices 500-1, 500-2, 500-3, ..., 500-(n-1), 500-n for respectively delaying one sampling period through a series connection thereof, a plurality of multipliers 501-1, 501-2, 501-3, 501-4, ..., 501-(n-1), 501-n, 501-(n+l) connected to input terminals or output terminals of each unit delay devices, and a plurality of adders 502-1, 502-2, 502-3, ..., 50-2(n-2), 502(n-1), 502-n for successively adding the outputs of each of the multipliers. A multiplying coefficient of each multiplier may be adjusted to determine an amount of phase shift. Further, the construction of the in-phase component detecting means 51 is the same as that of the in-phase component detecting 4, and thus a description thereof is omitted.
At this point, two microphones 1 are positioned symmetrically with respect to the driving seat 14, and asymmetrically with respect to the passenger seat 15.
Therefore, as the commands generated at the passenger seat 15 are out of phase in the electric signals from the microphones 1, in the phase shift means 50-1 and 50-2, the multiplying coefficients of the multipliers are adjusted to be in-phase with respect to the input signals. Accordingly, a certain amount of phase from the microphones 1 is shifted and adjusted so that the in-phase component detecting means 51 of the phase shift 9 2~ .7~
and in-phase component detecting means can superimpose voice signals from the two microphones 1 with respect to the commands from the passenger seat 5, at the output level thereof.
Further, with respect to the commands generated at the passenger seat 15, the in-phase component detecting means 4 cannot cause a superimposing of the voice signals from the two microphones 1 at the output level, since each electric signal has a phase shift.
Next, the command seat discriminating means 6 is described. The command seat discriminating means 6 consists of a comparator which outputs an "H (High)"
signal when Va _ Vb, or an "L (Low)" signal when Va < Vb; where the output signals of the in-phase component detecting means 4, and the phase shift and in-phase component detecting means 5 are represented by Va and Vb respectively. When the command seat discriminating means 6 outputs an "H" signal, the command is discriminated as generated at the driving seat 14, since Va _ Vb, i.e., the output level of the electric signals passing through the in-phase component detecting means 4 is higher than that of electric signals passing through the phase shift and in-phase component detecting means.
In the reverse case, the command is discriminated as generated at the passenger seat 15.
Next, the means 7 for determ;ning the validity and invalidity of commands is described. Figure 7 is a view showing a determination of the validity and invalidity of commands resulting from a speech recognition thereof.
As shown in this Figure, the means 7 for determining the validity and invalidity of command determines the command to be valid if the command is, for example, AUDIO ON/OFF, AIR CONDITIONING ON/OFF, NAVIGATION ON/OFF
VEHICLE CONTROL SET/RESUME, which can be recognized by the speech recognition means 3, and is discriminated as generated at the driving seat 14 by the command seat discriminating means 6. Also, the means 7 determines 20~9~. ~3 the command to be valid if the command is, for example, AUDIO ON/OFF, AIR CONDITIONING ON/OFF, NAVIGATION
ON/OFF, which can be recognized by the speech recognition means 3 and is discriminated as generated at the passenger seat 15 by the command seat discriminating means 6. The means 7 determines the command to be invalid if the command is, for example, VEHICLE CONTROL
SET/RESUME, which is recognized by the speech recognition means 3 and is discriminated as generated at the passenger seat by the command seat discriminating means 6. Accordingly, a voice command from the passenger seat cannot interfere with matters which the driver should determine from a vehicle control point of view, but can be used as a command for providing various services other than the above-mentioned matters.
Next, a series of operations in accordance with the embodiment is described. Figure 8 is a flowchart illustrating a consecutive operation in accordance with the first embodiment of the present invention. As shown in this Figure, analogue electric signals of the command received through the microphones 1 are converted into digital signals (step 1). The unknown pattern formed in the digital signals of the command is then processed by the speech recognition means 3 to determine whether or not it is a registered pattern (step 2). If the unknown pattern of the commands is the same as a registered pattern, the commands are processed by the in-phase component detecting means 4 to determine whether or not they are generated at the driving seat (step 3). If the commands are generated at the driving seat, the ON/OFF
control of the corresponding audio equipment 100, air conditioning equipment 101, telephone equipment 102, and navigation equipment 103, and the vehicle set/resume control 104 is performed, through the various controlling means 8 (step 4). Further, the control content passed through the various controlling means 8 is processed to be converted to voice signals by the 2~49~73 speech synthesizing means 9, is reproduced as speech through the D/A converter 10, the low pass filter 11 and the power amplifier 12, and is broadcast at the driving seat 14 (step 5). At step 3, if the commands are determined to be from the passenger seat 15, it is determined whether the commands are vehicle control commands (step 6). If these commands are not vehicle control commands but are, for example, audio equipment ON/OFF commands, the processing and control thereof are performed at step 4. If the commands are vehicle control commands, they are not processed and controlled but are broadcast at the driving seat 14 (step 5).
Figure 9A and 9B is a view of a speech recognition apparatus in accordance with a second embodiment of the present invention. The speech recognition apparatus shown in this Figure is the same as that of the first embodiment of Fig. 2A and 2B, except that rear seats 16 and 17 are included in the vehicle room 18, a microphone 1-1 is provided at the rear seat 16 near to the driving seat 14, a phase shift and in-phase component detecting means 5-1, 5-2 and 5-3 is provided for the passenger seat 15 and the rear seats 17 and 16, respectively, and a command seat discriminating means 6-1 is provided for comparing the output level of the in-phase component detecting means 4 and the m~;mum output level of the phase shift and in-phase component detecting means 5-1, 5-2 and 5-3. The phase shift and in-phase component detecting means 5-2 adjusted to detect the same in-phase signals from the two microphones 1, taking into consideration the asymmetrical positions thereof with respect to the rear seat 17, which is different from that of the passenger seat 15. Since the microphones 1 are symmetrical with respect to the rear seat 16, to prevent the danger of an error in a command at the driving seat 14, or conversely, in a command at the rear seat 16, the phase shift and in-phase component detecting means 5-3 is - 12 - 2~49~
adjusted to detect the same in-phase signals at each of the microphones 1 and the microphone 1-1, taking into consideration the asym.metrical position thereof with respect to the rear seat 16. Therefore, when command is given from the rear seat 16, in the in-phase component detecting means 4 and the phase shift and in-phase component detecting means 5-3, the output level of the latter become too great to be discriminated from a command from the driving seat 14. In the seat discriminating means 6-1, if the output level of the in-phase component detecting means 4 is greater than that of any phase shift and in-phase component detecting means 5-1, 5-2 and 5-3, the command is discriminated as being from the driving seat 14. Conversely, if it is smaller than that of any means 5-1, 5-2 and 5-3, the command is discriminated as being from a seat other than the driving seat 14.
Figure lOA and lOB is a view of a speech recognition apparatus in accordance with a third embodiment of the present invention. The speech recognition apparatus shown in this Figure is the same as that of the second embodiment of Fig. 9A and 9B, except that microphones 1-1, 1-2, 1-3, 1-4, 1-5 and 1-6 are positioned separate from each other, and input voice commands from each seat in the vehicle room, a phase shift means 19 for shifting phases of electric signals through the microphones and A/D converter with the same phase shift relative to each seat, an adding means 20 for adding output signals of the phase shift means 19 corresponding to said each seat, and a m~ximum amplitude signal detecting means 21 for detecting the m~imum amplitude signal of output signals of each adding means 20 as the voice commands to be output to the speech recognition means 3, are provided.
Next, the phase shift means 19 and the adding means 20 are described in detail. Figure 11 shows a processing circuit of phase shifting means and adding -- - 13 - ~ O ~
means for processing signals from each microphone provided at each seat of Fig. lOA and lOB. The phase shift means 19 shown in this Figure includes phase shifters 19-1, 19-2, 19-3 and 19-4 connected to the microphone 1-1 at the corresponding above four seats through an A/D converter 2, not shown in the Figure, and phase shifters 19-5, 19-6, 19-7 and 19-8 connected to the microphone 1-2, ..., and phase shifters 19-21, 19-22, 19-23 and 19-24 connected to the microphone 1-6.
The adding means 20 includes an adder 20-1 for adding outputs of the phase shifters 19-1, 19-5, 19-9, 19-13, 19-17 and 19-21, an adder 20-2 for adding outputs of the phase shifters 19-2, 19-6, 19-10, 19-14, 19-18 and 19-22, ..., and an adder 20-4 for adding outputs of the phase shifters 19-4, 19-8, 19-12, 19-16, 19-20 and 19-24.
Figure 12 shows the phase shifting means connected to the adding means 20-1 of Fig. 11. The phase shifter 19-1 in the phase shifting means 19 shown in this Figure includes an amplifier 300 connected to the microphone 1-1, a plurality of unit delay devices 301-1, 301-2, 301-3, ..., 301-(n-1) and 301-n connected in series, for delaying one sampling period of input signal from the amplifier 100, respectively, a plurality of multipliers 302-1, 302-2, 302-3, 302-4, ... , 302-(n-1) and 302-n connected to input terminals of each of the unit delay devices, and a plurality of adders 303-1, 303-2, 303-3, ..., 303-(n-2), 303-(n-1), 303-n for successively adding outputs of each of the multipliers.
Further, the phase shifter 19-5 includes an amplifier 316 connected to the microphone 1-2, a plurality of unit delay devices 317-1, 317-2, 317-3, ..., 317-(n-1) and 317-n connected in series, for delaying one sampling period of input signal from the amplifier 316, respectively, a plurality of multipliers 318-1, 318-2, 318-3, 318-4, ..., 318-(n-1) and 318-n connected to input terminals of each of the 2~ 7~
unit delay devices, and a plurality of adders 319-1, 319-2, 319-3, ..., 319-(n-2), 319-(n-1), 319-n for successively adding outputs of each of the multipliers ... . The phase shifter 19-21 includes an amplifier 380 connected to the microphone 1-6, a plurality of unit delay devices 381-1, 381-2, 381-3, ..., 381-(n-1) 381-n connected in series, for delaying one sampling period of input signal from the amplifier 380, respectively, a plurality of multipliers 382-1, 382-2, 382-3, 382-4, ... , 382-(n-1) and 382-n connected to input ter~in~ls of each of the unit delay devices, and adders 383-1, 383-2, 383-3, ..., 383-(n-2), 383-(n-1), 383-n for successively adding outputs of each of the multipliers. Also, the adding means 20-1 is provided with an adder 400 for adding outputs of the adders 303-n, 319-n, ... , and 383-n and an amplifier 401 for amplifying the output of the adder 400. For example, when the voice command is generated at the driving seat 14 as shown in Fig. 10A, the phases of the voice command received by the microphones 1-1, 1-2, ... , 1-6 is different, and thus an adjustment of the multiplying coefficients relative to each of the multipliers corresponding to each of the phase shifters 19-1, 19-5, ..., 19-21 causes the phase shifts due to differences in the positions of the microphones to be the same as each other. Accordingly, each signal from each of the microphones in the vehicle room 18 is shifted in phase so as to be the same as each other, and is added by the adding means 20-1 and is superimposed.
On the other hand, where the noise as shown in Fig. 10A comes from the left and right directions at a right angle to the vehicle running direction, or from the front and rear relative to the vehicle running direction, each microphone is positioned so as to produce a phase shift among the microphones 1-1, 1-2 and 1-3, among the microphones 1-4, 1-5 and 1-6, between the microphones 1-1 and 1-4, between the microphones 1-2 and - 15 - Z049~73 1-5, and between the microphones 1-3 and 1-6, with respect to the above-mentioned noise. Conversely, the microphones 1-1 and 1-2 or 1-4 and 1-5 are positioned relative to each other roughly symmetrically to the left and right with respect to the voice command from the driving seat 14, and further, the microphones 1-1 and 1-4 or 1-2 and 1-5 are positioned relative to each other roughly symmetrically to the front and rear thereof, whereby the phase shift means 19 adjusts the outputs of each microphone so that they are in the same phase as each other, whereby the level of the voice command received by each of the microphones is enhanced to thus improve the S/N relative to the noise. Note, with regard to the microphones 1-3 and 1-6 positioned asymmetrically at the left and right, and which make no contribution to a reduction of the noise level, the gain of the amplifier 332 of the phase shifter 19-9 and the amplifier 380 of the phase shifter 19-21 may be made zero. Although the above explanation has been made with regard to the driving seat 14, the explanation relative to the passenger seat 15, and the rear seats 16 and 17 is the same.
Next, the mA~imum amplitude signal detecting means 21 is described. Figure 13 shows a m~Ximum amplitude signal detecting means of Fig. lOA and lOB for a speech recognition. The m~imum amplitude signal detecting means as shown in this Figure includes absolute value processed means 60-1, 60-2, 60-3 and 60-4 connected to the adding means 20-1, 20-2, 20-3 and 20-4 as shown in Fig. 13, comparators 61-1, 61-2 and 61-3 each having a noninversion terminal thereof connected to the absolute value processed means 60-1 respectively, and an inversion terminal thereof connected to each of the absolute value processed means 60-2, 60-3 and 60-4 respectively, comparators 61-4, 61-5 and 61-6 each having a non inversion terminal is connected to the absolute value processed means 60-2 respectively, and an - 16 - ~04~73 inversion terminal thereof connected to each of the absolute value processed means 60-1, 60-3 and 60-4 respectively, ..., comparators 61-10, 61-11 and 61-12 each having a non inversion term; n~l thereof connected to the absolute value processed means 60-4 respectively, and an inversion terminal thereof connected to each of the absolute value processed means 60-1, 60-2 and 60-3, AND circuits 62-1, 62-2, 62-3 and 62-4 each having an input terminal connected to the output termi n~ls of the comparators 61-1, 61-2 and 61-3, 61-4, 61-5 and 61-6, 61-7, 61-8 and 61-9, and 61-10, 61-11 and 61-12 respectively, gate circuits 63-1, 63-2, 63-3 and 63-4 for controlling each of the output signals of the adding means 20-1, 20-2, 20-3 and 20-4 by each of outputs of the AND circuits 62-1, 62-2, 62-3 and 62-4 respectively, and an OR circuit having input terminals connected to each of the output terminals of the gate circuits 63-1, 63-2, 63-3 and 63-4. With respect to the driving seat 14, the passenger seat 15, and the rear seats 16, and 17, the signals from the adding means 20-1, 20-2, 20-3 and 20-4, which are processed to be shifted in phase and added, are compared by the comparators 61-1, 61-2, ..., 61-12 through the absolute value processing means 60-1, 60-2, 60-3 and 60-4, whereby for example, when the voice commands are generated at the driving seat 14, the m~ximum amplitude signals relative to the driving seat 14 are selected by the AND circuit 62-1 to thereby control the gate circuit 63-1 corresponding to the AND circuit 62-1 and detected through the OR circuit 64. In this case, with respect to the passenger seat 15 and the rear seats 16 and 17, but not to the driving seat 14, signals which are shifted in phase and added do not include superimposed components and thus do not have a m~ximum amplitude. Accordingly, the microphones 1-1, 1-2, ... , 1-6 have a directivity relative to the driving seat 14, the passenger seat 15, and the rear seats 16 and 17 according to the positions 2~-g~
of the microphones, the phase shift means 19, the adding means 20 and the m~ximl1m amplitude signal detecting means 21.
Further, in the speech recognition apparatus in accordance with a fourth embodiment of the present invention signals can be input to the speech recognition means 3 not only from the A/D converter 2 through the center microphone 1 as in the first and the second embodiments respectively shown in the Fig. 2A and 2B, and 9A and 9B, but also from the command seat discriminating means 6, to thereby obtain a signal which is detected as a m~X; mum amplitude signal as it is, in the same way as in the third embodiment, to obtain a highly accurate speech recognition.
The present invention provides a speech recognition apparatus having a high discriminative reliability and a high recognition enhancement, due to the use of different phase shifts of signals obtained by a plurality of microphones positioned at a driving seat, a passenger seat and rear seats of the vehicle.
Claims (4)
1. A speech recognition apparatus having microphones installed inside a vehicle, and a speech recognition means for recognizing a voice command by which various equipment installed inside the vehcile can be controlled, characterized in that it comprises:
an in-phase component detecting means for detecting an in-phase component of voice signals of the microphones positioned symmetrically with respect to one seat, to obtain a command generated at said one seat, a phase shift and in-phase component detecting means for detecting an in-phase component after shifting a certain amount of a voice signal phase from the microphones positioned asymmetrically with respect to other seats, to thereby obtain the same phase shifts and a command generated at said other seats, a command seat discriminating means for comparing outputs levels of said in-phase component detecting means and said phase shift and in-phase component detecting means to discriminate from which seat a command is generated, among several seats, a determining means for determining a validity and invali-dity of commands resulting from speech obtained from outputs of said speech recognition means and said command seat discrimina-ting means to thereby control the various equipment.
an in-phase component detecting means for detecting an in-phase component of voice signals of the microphones positioned symmetrically with respect to one seat, to obtain a command generated at said one seat, a phase shift and in-phase component detecting means for detecting an in-phase component after shifting a certain amount of a voice signal phase from the microphones positioned asymmetrically with respect to other seats, to thereby obtain the same phase shifts and a command generated at said other seats, a command seat discriminating means for comparing outputs levels of said in-phase component detecting means and said phase shift and in-phase component detecting means to discriminate from which seat a command is generated, among several seats, a determining means for determining a validity and invali-dity of commands resulting from speech obtained from outputs of said speech recognition means and said command seat discrimina-ting means to thereby control the various equipment.
2. A speech recognition apparatus according to claim 1, characterized in that:
said speech recognition means recognizes an input of a signal from said in-phase component detecting means or said phase shift and in-phase component detecting means, which is detected in the same way as in said command seat discriminating means in order to compare an unknown speech pattern with a registered speech pattern.
said speech recognition means recognizes an input of a signal from said in-phase component detecting means or said phase shift and in-phase component detecting means, which is detected in the same way as in said command seat discriminating means in order to compare an unknown speech pattern with a registered speech pattern.
3. A speech recognition apparatus according to claim 1, characterized in that:
said microphones are arranged asymmetrically with respect to a passenger seat and rear seats of a vehicle, and comprises a phase shift and in-phase component detecting means which obtains commands from the passenger seat and the rear seats, respectively, from the voice signals of said microphones.
said microphones are arranged asymmetrically with respect to a passenger seat and rear seats of a vehicle, and comprises a phase shift and in-phase component detecting means which obtains commands from the passenger seat and the rear seats, respectively, from the voice signals of said microphones.
4. A speech recognition apparatus having microphones installed inside a vehicle, and a speech recognition means for recognizing voice commands by which various equipment installed inside the vehicle can be controlled, characterized in that:
said microphones are separated from each other to thus input voice commands generated at each seat in the vehicle, and comprising a phase shift means for shifting a predetermined amount of phases of electric signals sent through the microphones with the same phase shift relative to each seat, an adding means for adding output signals of said phase shift means corresponding to said each seat, a maximum amplitude signal detecting means for detecting a maximum amplitude signal of output signals of each adding means as voice commands and outputting same to the speech recognition means.
said microphones are separated from each other to thus input voice commands generated at each seat in the vehicle, and comprising a phase shift means for shifting a predetermined amount of phases of electric signals sent through the microphones with the same phase shift relative to each seat, an adding means for adding output signals of said phase shift means corresponding to said each seat, a maximum amplitude signal detecting means for detecting a maximum amplitude signal of output signals of each adding means as voice commands and outputting same to the speech recognition means.
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2214953A JPH0652477B2 (en) | 1990-08-16 | 1990-08-16 | Voice recognizer |
| JP2-214953 | 1990-08-16 | ||
| JP2238877A JPH0756596B2 (en) | 1990-09-11 | 1990-09-11 | Voice recognizer |
| JP2-238877 | 1990-09-11 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CA2049173A1 CA2049173A1 (en) | 1992-02-17 |
| CA2049173C true CA2049173C (en) | 1996-06-25 |
Family
ID=26520607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA002049173A Expired - Fee Related CA2049173C (en) | 1990-08-16 | 1991-08-14 | Speech recognition apparatus |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US5214707A (en) |
| EP (1) | EP0472356B1 (en) |
| CA (1) | CA2049173C (en) |
| DE (1) | DE69101527T2 (en) |
Families Citing this family (96)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2687496B1 (en) * | 1992-02-18 | 1994-04-01 | Alcatel Radiotelephone | METHOD FOR REDUCING ACOUSTIC NOISE IN A SPEAKING SIGNAL. |
| DE4315000A1 (en) * | 1993-05-06 | 1994-11-10 | Opel Adam Ag | Noise-compensated hands-free system in motor vehicles |
| US5657425A (en) * | 1993-11-15 | 1997-08-12 | International Business Machines Corporation | Location dependent verbal command execution in a computer based control system |
| US5568559A (en) * | 1993-12-17 | 1996-10-22 | Canon Kabushiki Kaisha | Sound processing apparatus |
| US5459957A (en) * | 1994-06-09 | 1995-10-24 | Winer; Guy T. | Gun security and safety system |
| JP3530591B2 (en) * | 1994-09-14 | 2004-05-24 | キヤノン株式会社 | Speech recognition apparatus, information processing apparatus using the same, and methods thereof |
| JP2674521B2 (en) * | 1994-09-21 | 1997-11-12 | 日本電気株式会社 | Mobile object guidance device |
| ATE196560T1 (en) * | 1994-12-23 | 2000-10-15 | Siemens Ag | METHOD FOR CONVERTING VOICE ENTRED INFORMATION INTO MACHINE READABLE DATA |
| US5828997A (en) * | 1995-06-07 | 1998-10-27 | Sensimetrics Corporation | Content analyzer mixing inverse-direction-probability-weighted noise to input signal |
| US5734727A (en) * | 1995-06-07 | 1998-03-31 | Asc Incorporated | Sunroof assembly noise attenuation system |
| US5774858A (en) * | 1995-10-23 | 1998-06-30 | Taubkin; Vladimir L. | Speech analysis method of protecting a vehicle from unauthorized accessing and controlling |
| FR2744277B1 (en) * | 1996-01-26 | 1998-03-06 | Sextant Avionique | VOICE RECOGNITION METHOD IN NOISE AMBIENCE, AND IMPLEMENTATION DEVICE |
| US6073101A (en) | 1996-02-02 | 2000-06-06 | International Business Machines Corporation | Text independent speaker recognition for transparent command ambiguity resolution and continuous access control |
| US6009355A (en) | 1997-01-28 | 1999-12-28 | American Calcar Inc. | Multimedia information and control system for automobiles |
| US5924070A (en) * | 1997-06-06 | 1999-07-13 | International Business Machines Corporation | Corporate voice dialing with shared directories |
| US5897616A (en) | 1997-06-11 | 1999-04-27 | International Business Machines Corporation | Apparatus and methods for speaker verification/identification/classification employing non-acoustic and/or acoustic models and databases |
| US6148261A (en) * | 1997-06-20 | 2000-11-14 | American Calcar, Inc. | Personal communication system to send and receive voice data positioning information |
| US6275231B1 (en) * | 1997-08-01 | 2001-08-14 | American Calcar Inc. | Centralized control and management system for automobiles |
| DE19735504A1 (en) * | 1997-08-16 | 1999-02-18 | Magna Sitzsysteme Gmbh Mse Sea | Seat adjustment device |
| FR2772959B1 (en) * | 1997-12-22 | 2000-06-02 | Renault | METHOD FOR ORDERING SERVICES AVAILABLE TO OCCUPANTS OF A MOTOR VEHICLE |
| DE19812697A1 (en) | 1998-03-23 | 1999-09-30 | Volkswagen Ag | Method and device for operating a microphone arrangement, in particular in a motor vehicle |
| US6314401B1 (en) * | 1998-05-29 | 2001-11-06 | New York State Technology Enterprise Corporation | Mobile voice verification system |
| US6928614B1 (en) | 1998-10-13 | 2005-08-09 | Visteon Global Technologies, Inc. | Mobile office with speech recognition |
| US6240347B1 (en) | 1998-10-13 | 2001-05-29 | Ford Global Technologies, Inc. | Vehicle accessory control with integrated voice and manual activation |
| JP3619380B2 (en) * | 1998-12-25 | 2005-02-09 | 富士通株式会社 | In-vehicle input / output device |
| JP2001075594A (en) * | 1999-08-31 | 2001-03-23 | Pioneer Electronic Corp | Voice recognition system |
| DE19942868A1 (en) * | 1999-09-08 | 2001-03-15 | Volkswagen Ag | Method for operating a multiple microphone arrangement in a motor vehicle and a multiple microphone arrangement itself |
| DE19943872A1 (en) * | 1999-09-14 | 2001-03-15 | Thomson Brandt Gmbh | Device for adjusting the directional characteristic of microphones for voice control |
| DE19946559A1 (en) * | 1999-09-29 | 2001-04-05 | Zahnradfabrik Friedrichshafen | Control of an automatic or automated transmission via voice input |
| DE19962218C2 (en) * | 1999-12-22 | 2002-11-14 | Siemens Ag | Method and system for authorizing voice commands |
| US7187947B1 (en) | 2000-03-28 | 2007-03-06 | Affinity Labs, Llc | System and method for communicating selected information to an electronic device |
| US20020031234A1 (en) * | 2000-06-28 | 2002-03-14 | Wenger Matthew P. | Microphone system for in-car audio pickup |
| JP2002049403A (en) * | 2000-08-07 | 2002-02-15 | Shin Caterpillar Mitsubishi Ltd | Voice operated controller for construction equipment |
| JP2004509018A (en) * | 2000-09-21 | 2004-03-25 | アメリカン カルカー インコーポレイティド | Operation support method, user condition determination method, tire condition determination method, visibility measurement method, road determination method, monitor device, and operation device |
| US8990367B2 (en) * | 2006-09-29 | 2015-03-24 | Dell Products L.P. | Consistent binding of shared storage across clustered servers |
| US6529608B2 (en) | 2001-01-26 | 2003-03-04 | Ford Global Technologies, Inc. | Speech recognition system |
| DE10204325B4 (en) * | 2001-02-01 | 2005-10-20 | Vbv Vitamin B Venture Gmbh | Method and device for automatic speech recognition |
| DE10120679A1 (en) * | 2001-04-27 | 2002-05-02 | Siemens Ag | Device for voice control of safety-relevant functions has connection between voice recognition and subsequent stages only released by operator signal after successful indication |
| EP1438669B1 (en) | 2001-06-27 | 2014-01-22 | SKKY Incorporated | Improved media delivery platform |
| DE10140097B4 (en) * | 2001-08-16 | 2005-04-28 | Guenter Fendt | Method for assisting an operator of a device in finding the position of a control element |
| US6937980B2 (en) * | 2001-10-02 | 2005-08-30 | Telefonaktiebolaget Lm Ericsson (Publ) | Speech recognition using microphone antenna array |
| US6801632B2 (en) | 2001-10-10 | 2004-10-05 | Knowles Electronics, Llc | Microphone assembly for vehicular installation |
| US20030090161A1 (en) * | 2001-10-19 | 2003-05-15 | Marlow C. Allen | Light communication channel-based electronics power distribution system |
| US6772733B2 (en) | 2001-10-19 | 2004-08-10 | Visteon Global Technologies, Inc. | Optically controlled IPCS circuitry |
| US20030095675A1 (en) * | 2001-10-19 | 2003-05-22 | Marlow C. Allen | Light communication channel-based voice-activated control system and method for implementing thereof |
| US7024067B2 (en) * | 2001-10-19 | 2006-04-04 | Visteon Global Technologies, Inc. | Communication system with a signal conduction matrix and surface signal router |
| US6949758B2 (en) * | 2001-10-19 | 2005-09-27 | Visteon Global Technologies, Inc. | LCC-based fluid-level detection sensor |
| DE10156738A1 (en) * | 2001-11-19 | 2003-06-05 | Stefan Kleeberg | Data communications device for motor vehicles, has transmitter-receiver device for sending and receiving suitable signals, enables optical signals to be transmitted and received in visible range |
| DE10156954B9 (en) * | 2001-11-20 | 2005-07-14 | Daimlerchrysler Ag | Image-based adaptive acoustics |
| US20030162572A1 (en) * | 2002-02-27 | 2003-08-28 | Winters Kenneth W. | Information system methods and apparatus |
| DE10208465A1 (en) * | 2002-02-27 | 2003-09-18 | Bsh Bosch Siemens Hausgeraete | Electrical device, in particular extractor hood |
| JP3724461B2 (en) * | 2002-07-25 | 2005-12-07 | 株式会社デンソー | Voice control device |
| US6978199B2 (en) * | 2003-01-15 | 2005-12-20 | Daimlerchrysler Corporation | Method and apparatus for assisting vehicle operator |
| US9818136B1 (en) | 2003-02-05 | 2017-11-14 | Steven M. Hoffberg | System and method for determining contingent relevance |
| DE10320209B4 (en) * | 2003-05-07 | 2005-12-01 | Sennheiser Electronic Gmbh & Co. Kg | Audio signal detection system |
| JP4145835B2 (en) * | 2004-06-14 | 2008-09-03 | 本田技研工業株式会社 | In-vehicle electronic control unit |
| DE102004030054A1 (en) * | 2004-06-22 | 2006-01-12 | Bayerische Motoren Werke Ag | Method for speaker-dependent speech recognition in a motor vehicle |
| US7188012B2 (en) * | 2004-08-24 | 2007-03-06 | Ford Global Technologies, Llc | Adaptive voice control and vehicle collision warning and countermeasure system |
| JP4097219B2 (en) * | 2004-10-25 | 2008-06-11 | 本田技研工業株式会社 | Voice recognition device and vehicle equipped with the same |
| CN1815556A (en) * | 2005-02-01 | 2006-08-09 | 松下电器产业株式会社 | Method and system capable of operating and controlling vehicle using voice instruction |
| DE602005008005D1 (en) | 2005-02-23 | 2008-08-21 | Harman Becker Automotive Sys | Speech recognition system in a motor vehicle |
| WO2007030638A2 (en) * | 2005-09-08 | 2007-03-15 | Johnson Controls Technology Company | Front supervision of rear seat entertainment system |
| US8874477B2 (en) | 2005-10-04 | 2014-10-28 | Steven Mark Hoffberg | Multifactorial optimization system and method |
| US11084377B2 (en) | 2005-11-17 | 2021-08-10 | Invently Automotive Inc. | Vehicle power management system responsive to voice commands from a Gps enabled device |
| US10882399B2 (en) | 2005-11-17 | 2021-01-05 | Invently Automotive Inc. | Electric vehicle power management system |
| US7870142B2 (en) * | 2006-04-04 | 2011-01-11 | Johnson Controls Technology Company | Text to grammar enhancements for media files |
| WO2007123797A1 (en) | 2006-04-04 | 2007-11-01 | Johnson Controls Technology Company | System and method for extraction of meta data from a digital media storage device for media selection in a vehicle |
| ATE410346T1 (en) * | 2006-08-04 | 2008-10-15 | Harman Becker Automotive Sys | METHOD AND SYSTEM FOR PROCESSING VOICE COMMANDS IN A VEHICLE ENVIRONMENT |
| WO2008019709A1 (en) * | 2006-08-17 | 2008-02-21 | Snap-On Incorporated | Vehicle diagnostic equipment providing hands free operation |
| US8214219B2 (en) * | 2006-09-15 | 2012-07-03 | Volkswagen Of America, Inc. | Speech communications system for a vehicle and method of operating a speech communications system for a vehicle |
| DE102006047982A1 (en) | 2006-10-10 | 2008-04-24 | Siemens Audiologische Technik Gmbh | Method for operating a hearing aid, and hearing aid |
| US8255123B2 (en) * | 2007-06-27 | 2012-08-28 | GM Global Technology Operations LLC | Apparatus and method for positioning a movable component of a motor actuated device |
| US8103671B2 (en) * | 2007-10-11 | 2012-01-24 | Honda Motor Co., Ltd. | Text categorization with knowledge transfer from heterogeneous datasets |
| JP2011503638A (en) * | 2007-10-26 | 2011-01-27 | 本田技研工業株式会社 | Improvement of free conversation command classification for car navigation system |
| DE102009005674B3 (en) * | 2009-01-22 | 2010-04-15 | Recaro Gmbh & Co. Kg | Control device for a vehicle seat |
| DE102009039889B4 (en) * | 2009-09-03 | 2021-10-07 | Volkswagen Ag | Device and method for capturing speech in a motor vehicle |
| DE102009051508B4 (en) * | 2009-10-30 | 2020-12-03 | Continental Automotive Gmbh | Device, system and method for voice dialog activation and guidance |
| US20110208604A1 (en) * | 2010-02-20 | 2011-08-25 | Yang Pan | Media Delivery System for an Automobile by the Use of Voice Input Device and Head-Up Display |
| US9073433B2 (en) * | 2011-08-23 | 2015-07-07 | Continental Automotive Systems, Inc | Vehicle control system |
| WO2014063104A2 (en) * | 2012-10-19 | 2014-04-24 | Audience, Inc. | Keyword voice activation in vehicles |
| US9508345B1 (en) | 2013-09-24 | 2016-11-29 | Knowles Electronics, Llc | Continuous voice sensing |
| FR3011435B1 (en) * | 2013-09-30 | 2019-07-12 | Dav | LIGHT DEVICE FOR VISUALIZING A CONTROL OF A FUNCTION |
| US9431013B2 (en) | 2013-11-07 | 2016-08-30 | Continental Automotive Systems, Inc. | Co-talker nulling for automatic speech recognition systems |
| US9953634B1 (en) | 2013-12-17 | 2018-04-24 | Knowles Electronics, Llc | Passive training for automatic speech recognition |
| US9437188B1 (en) | 2014-03-28 | 2016-09-06 | Knowles Electronics, Llc | Buffered reprocessing for multi-microphone automatic speech recognition assist |
| US9530407B2 (en) * | 2014-06-11 | 2016-12-27 | Honeywell International Inc. | Spatial audio database based noise discrimination |
| US10013981B2 (en) | 2015-06-06 | 2018-07-03 | Apple Inc. | Multi-microphone speech recognition systems and related techniques |
| US9865265B2 (en) | 2015-06-06 | 2018-01-09 | Apple Inc. | Multi-microphone speech recognition systems and related techniques |
| US10079027B2 (en) * | 2016-06-03 | 2018-09-18 | Nxp B.V. | Sound signal detector |
| CN107757626A (en) * | 2016-08-19 | 2018-03-06 | 上汽通用汽车有限公司 | A kind of acoustic control shifting control system |
| CN107554456A (en) * | 2017-08-31 | 2018-01-09 | 上海博泰悦臻网络技术服务有限公司 | Vehicle-mounted voice control system and its control method |
| DE102018009487A1 (en) * | 2018-12-03 | 2020-06-04 | Daimler Ag | Method and device for adjusting a vehicle component |
| KR20200072026A (en) * | 2018-12-12 | 2020-06-22 | 현대자동차주식회사 | Apparatus and method for speech recognition processing |
| US11318955B2 (en) | 2019-02-28 | 2022-05-03 | Google Llc | Modalities for authorizing access when operating an automated assistant enabled vehicle |
| CN111660773B (en) * | 2020-05-29 | 2023-02-03 | 奇瑞汽车股份有限公司 | Sound control window method and system applied to automobile |
| CN114743552A (en) * | 2022-03-22 | 2022-07-12 | 大连理工大学 | Semantic recognition and voice positioning based child safety seat rotation control method |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3644674A (en) * | 1969-06-30 | 1972-02-22 | Bell Telephone Labor Inc | Ambient noise suppressor |
| US3784747A (en) * | 1971-12-03 | 1974-01-08 | Bell Telephone Labor Inc | Speech suppression by predictive filtering |
| US4354059A (en) * | 1979-09-11 | 1982-10-12 | Victor Company Of Japan, Ltd. | Variable-directivity microphone device |
| JPS56117497A (en) * | 1980-02-22 | 1981-09-14 | Nippon Telegr & Teleph Corp <Ntt> | Adjuster of directive microphone |
| DE3273523D1 (en) * | 1982-05-19 | 1986-11-06 | Nissan Motor | Speech recognition system for an automotive vehicle |
| FR2559325B1 (en) * | 1984-02-06 | 1986-08-22 | Renault | APPARATUS FOR CAPTURING AND TRANSMITTING THE WORD OF A PERSON PLACED IN A DISTURBED ENVIRONMENT IN ORDER TO PERFORM A PROCESSING OF THIS WORD |
| US4626796A (en) * | 1985-03-01 | 1986-12-02 | General Electric Company | Digital apparatus and method for programmably phase shifting an audio tone |
| DE8529437U1 (en) * | 1985-10-16 | 1987-06-11 | Siemens Ag, 1000 Berlin Und 8000 Muenchen, De | |
| US4827520A (en) * | 1987-01-16 | 1989-05-02 | Prince Corporation | Voice actuated control system for use in a vehicle |
| JPH0277799A (en) * | 1988-09-14 | 1990-03-16 | Clarion Co Ltd | On-vehicle speech recognition device |
-
1991
- 1991-08-14 EP EP91307499A patent/EP0472356B1/en not_active Expired - Lifetime
- 1991-08-14 DE DE69101527T patent/DE69101527T2/en not_active Expired - Fee Related
- 1991-08-14 CA CA002049173A patent/CA2049173C/en not_active Expired - Fee Related
- 1991-08-16 US US07/745,759 patent/US5214707A/en not_active Expired - Lifetime
Also Published As
| Publication number | Publication date |
|---|---|
| EP0472356A1 (en) | 1992-02-26 |
| EP0472356B1 (en) | 1994-03-30 |
| DE69101527T2 (en) | 1994-07-14 |
| DE69101527D1 (en) | 1994-05-05 |
| US5214707A (en) | 1993-05-25 |
| CA2049173A1 (en) | 1992-02-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2049173C (en) | Speech recognition apparatus | |
| Meyer et al. | Multi-channel speech enhancement in a car environment using Wiener filtering and spectral subtraction | |
| JP2776848B2 (en) | Denoising method, neural network learning method used for it | |
| US5400409A (en) | Noise-reduction method for noise-affected voice channels | |
| US6411928B2 (en) | Apparatus and method for recognizing voice with reduced sensitivity to ambient noise | |
| WO2003028006A2 (en) | Selective sound enhancement | |
| US6690805B1 (en) | Audio signal noise reduction system | |
| JP2003271191A (en) | Device and method for suppressing noise for voice recognition, device and method for recognizing voice, and program | |
| JP2001075594A (en) | Voice recognition system | |
| JP4005203B2 (en) | In-vehicle speech recognition device | |
| JPH05134694A (en) | Voice recognizing device | |
| CN105810210B (en) | Sound signal processing apparatus, sound signal processing method, and vehicle equipped with the apparatus | |
| JPH11249693A (en) | Sound collecting device | |
| JP3163109B2 (en) | Multi-directional simultaneous voice pickup speech recognition method | |
| JPH0497400A (en) | Voice recognition device | |
| JP3257832B2 (en) | Noise reduction circuit for speech recognition device | |
| JP2861011B2 (en) | Voice input method and device | |
| US6959277B2 (en) | Voice feature extraction device | |
| JPH04119400A (en) | Speech recognition device | |
| JP2965301B2 (en) | Sound collector | |
| JP2007028391A (en) | Microphone array device | |
| US6256394B1 (en) | Transmission system for correlated signals | |
| JP3949774B2 (en) | Volume control system | |
| CN114402630A (en) | Sound processing system and sound processing apparatus | |
| JP2990051B2 (en) | Voice recognition device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| EEER | Examination request | ||
| MKLA | Lapsed | ||
| MKLA | Lapsed |
Effective date: 20100816 |