CN112133297A - Voice recognition method, device and system - Google Patents
Voice recognition method, device and system Download PDFInfo
- Publication number
- CN112133297A CN112133297A CN202010911281.1A CN202010911281A CN112133297A CN 112133297 A CN112133297 A CN 112133297A CN 202010911281 A CN202010911281 A CN 202010911281A CN 112133297 A CN112133297 A CN 112133297A
- Authority
- CN
- China
- Prior art keywords
- signal
- noise
- noise signal
- audio signal
- identified
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10K—SOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
- G10K11/00—Methods or devices for transmitting, conducting or directing sound in general; Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
- G10K11/16—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
- G10K11/175—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound
- G10K11/178—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound by electro-acoustically regenerating the original acoustic waves in anti-phase
- G10K11/1781—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound by electro-acoustically regenerating the original acoustic waves in anti-phase characterised by the analysis of input or output signals, e.g. frequency range, modes, transfer functions
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10K—SOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
- G10K11/00—Methods or devices for transmitting, conducting or directing sound in general; Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
- G10K11/16—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
- G10K11/175—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound
- G10K11/178—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound by electro-acoustically regenerating the original acoustic waves in anti-phase
- G10K11/1785—Methods, e.g. algorithms; Devices
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10K—SOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
- G10K11/00—Methods or devices for transmitting, conducting or directing sound in general; Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
- G10K11/16—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
- G10K11/175—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound
- G10K11/178—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound by electro-acoustically regenerating the original acoustic waves in anti-phase
- G10K11/1785—Methods, e.g. algorithms; Devices
- G10K11/17853—Methods, e.g. algorithms; Devices of the filter
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
- G10L19/04—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using predictive techniques
- G10L19/26—Pre-filtering or post-filtering
Abstract
The invention provides a voice recognition method, a device and a system, wherein the method comprises the following steps: receiving a first noise signal sent by an external first acquisition module; generating a second noise signal according to the first noise signal; sending the second noise signal to an external conversion module so that the conversion module plays a noise reduction audio signal generated according to the second noise signal, wherein the amplitude of the noise signal obtained by superposing the noise reduction audio signal and the first noise signal is smaller than that of the first noise signal; and receiving an audio signal to be identified sent by an external second acquisition module, and identifying the audio signal to be identified, wherein the audio signal to be identified comprises a noise signal obtained by superposing a first noise signal and a noise reduction audio signal. The scheme can improve the accuracy of voice recognition.
Description
Technical Field
The present invention relates to the field of speech recognition technologies, and in particular, to a speech recognition method, apparatus, and system.
Background
Since various noises emitted by the household electrical appliance and noises in the environment have different influences on the voice recognition, the noise reduction of the voice recognition is very necessary. At present, after an audio signal (including a noise signal and a speech signal) is picked up by a speech recognition system, a noise feature is recognized according to an algorithm, and the noise signal is filtered from the audio signal, that is, only the speech signal is reserved for subsequent speech recognition.
The Chinese invention patent application with the application number of 201911369839.1 discloses a control system for voice acquisition and recognition and an implementation method thereof, and the invention is mainly characterized in that the invention provides a control system for voice acquisition and voice recognition, which has low power consumption and an active noise reduction function, can reduce the power consumption burden of the system caused by voice recognition, can realize the active noise reduction of the system, and improves the success rate of voice recognition.
The method aims at the problem that the existing voice recognition method can only filter noise signals in picked audio signals and cannot reduce the noise signals in the voice recognition process, so that when the picked noise signals are complex, the accuracy of voice recognition results is low.
Disclosure of Invention
The invention provides a voice recognition method, a voice recognition device and a voice recognition system, which can improve the accuracy of voice recognition.
In a first aspect, an embodiment of the present invention provides a speech recognition method, including:
receiving a first noise signal sent by an external first acquisition module;
generating a second noise signal according to the first noise signal;
sending the second noise signal to an external conversion module so that the conversion module plays a noise reduction audio signal generated according to the second noise signal, wherein the amplitude of a noise signal obtained by superposing the noise reduction audio signal and the first noise signal is smaller than that of the first noise signal;
and receiving an audio signal to be identified sent by an external second acquisition module, and identifying the audio signal to be identified, wherein the audio signal to be identified comprises a noise signal obtained by superposing the first noise signal and the noise reduction audio signal.
In one possible design, the generating a second noise signal from the first noise signal includes:
determining a first spectrum of the first noise signal;
generating a second spectrum from the first spectrum, wherein the second spectrum is in phase opposition to the first spectrum;
and generating the second noise signal according to the second frequency spectrum, wherein the first noise signal and the second noise signal have the same amplitude and the opposite phase.
In one possible design of the system, the system may be,
the conversion module comprises an FIR filter;
the FIR filter is used for generating the noise reduction audio signal according to the second noise signal;
the identifying the audio signal to be identified includes:
analyzing a third noise signal in the audio signal to be identified;
after the identifying the audio signal to be identified, further comprising:
and judging whether the third noise signal is converged, if not, determining a third frequency spectrum of the third noise signal, generating a correction coefficient of the FIR filter according to the first frequency spectrum, the second frequency spectrum and the third frequency spectrum, and adjusting the FIR filter by using the correction coefficient.
In a second aspect, an embodiment of the present invention further provides a speech recognition apparatus, including: a processing unit, a sending unit and a recognition unit;
the processing unit is used for receiving a first noise signal sent by an external first acquisition module and generating a second noise signal according to the first noise signal;
the transmitting unit is configured to transmit the second noise signal generated by the processing unit to an external conversion module, so that the conversion module plays a noise reduction audio signal generated according to the second noise signal, where an amplitude of a noise signal obtained by superimposing the noise reduction audio signal and the first noise signal is smaller than an amplitude of the first noise signal;
the identification unit is used for receiving an audio signal to be identified sent by an external second acquisition module and identifying the audio signal to be identified, wherein the audio signal to be identified comprises a noise signal obtained by superposing the first noise signal and the noise reduction audio signal.
In one possible design of the system, the system may be,
the processing unit is used for executing the following processing:
determining a first spectrum of the first noise signal;
generating a second spectrum from the first spectrum, wherein the second spectrum is in phase opposition to the first spectrum;
and generating the second noise signal according to the second frequency spectrum, wherein the first noise signal and the second noise signal have the same amplitude and the opposite phase.
In one possible design of the system, the system may be,
the conversion module comprises an FIR filter, wherein the FIR filter is used for generating the noise reduction audio signal according to the second noise signal;
the identification unit is used for analyzing a third noise signal in the audio signal to be identified;
the speech recognition apparatus further includes: an adjustment unit;
the adjusting unit is configured to determine whether the third noise signal analyzed by the identifying unit converges, determine a third frequency spectrum of the third noise signal if the third noise signal does not converge, generate a correction coefficient of the FIR filter according to the first frequency spectrum, the second frequency spectrum, and the third frequency spectrum, and adjust the FIR filter by using the correction coefficient.
In a third aspect, an embodiment of the present invention further provides a speech recognition system, including: the speech recognition apparatus, the first acquisition module, the conversion module and the second acquisition module provided in the second aspect or any possible implementation manner of the second aspect;
the first acquisition module is used for acquiring a first noise signal and sending the first noise signal to the voice recognition device;
the conversion module is configured to receive a second noise signal sent by the speech recognition device, generate a noise reduction audio signal according to the second noise signal, and play the noise reduction audio signal, where an amplitude of a noise signal obtained by superimposing the noise reduction audio signal and the first noise signal is smaller than an amplitude of the first noise signal;
the second acquisition module is used for acquiring an audio signal to be identified and sending the audio signal to be identified to the voice recognition device, wherein the audio signal to be identified comprises the noise signal obtained by superposing the first noise signal and the noise reduction audio signal.
In one possible design of the system, the system may be,
when the voice recognition system is deployed on target equipment, the distance between the first acquisition module and a target part of the target equipment, which emits noise, is smaller than a preset value;
the first acquisition module is used for carrying out noise acquisition on the target part to obtain the first noise signal, wherein the first noise signal comprises noise emitted by the target part;
the first acquisition module comprises: a microphone, a first signal amplifier, a first low-pass filter and a first analog-to-digital converter,
wherein the microphone is used for converting the collected first noise into a first noise analog signal;
the first signal amplifier is used for amplifying the first noise analog signal;
the first low-pass filter is used for performing low-pass filtering on the first noise analog signal amplified by the first signal amplifier and outputting a filtered analog signal;
the first analog-to-digital converter is configured to convert the analog signal filtered by the low-pass filter into the first noise signal, where the first noise signal is a digital signal;
the conversion module includes: an FIR filter, a digital-to-analog converter, a second low pass filter, a power amplifier and a loudspeaker,
wherein the FIR filter is configured to generate the noise reduction audio signal according to the second noise signal, and both the second noise signal and the noise reduction audio signal are digital signals;
the digital-to-analog converter is used for converting the noise reduction audio signal in the digital signal format into the noise reduction audio signal in the analog signal format;
the second low-pass filter is used for low-pass filtering the noise reduction audio signal in the analog signal format;
the power amplifier is used for amplifying the filtered noise reduction audio signal;
the loudspeaker is used for playing the noise reduction audio signal amplified by the power amplifier;
the second acquisition module comprises: a microphone array, a second signal amplifier, a third low-pass filter and a second analog-to-data converter,
the microphone array is used for converting collected sounds to be identified into analog signals to be identified;
the second signal amplifier is used for amplifying the analog signal to be identified;
the third low-pass filter is used for performing low-pass filtering on the analog signal to be identified;
the second analog-to-data converter is used for converting the filtered analog signal to be identified into an audio signal to be identified, and the audio signal to be identified is a digital signal.
In a fourth aspect, an embodiment of the present invention further provides an intelligent device, including: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor is configured to invoke the machine-readable program to perform the speech recognition method provided by the first aspect or any possible implementation manner of the first aspect.
In a fifth aspect, embodiments of the invention also provide a computer-readable medium,
the computer readable medium has stored thereon computer instructions, which, when executed by a processor, cause the processor to perform the speech recognition method provided by the first aspect or any of the possible implementations of the first aspect.
As can be seen from the foregoing technical solutions, in the speech recognition method provided in the embodiment of the present invention, the second noise signal is generated according to the received first noise signal, the external conversion module plays the noise reduction audio signal generated according to the second noise signal, and the audio signal to be recognized from the second acquisition module is recognized. Therefore, the amplitude of the noise signal obtained by superposing the noise reduction audio signal and the first noise signal is smaller than that of the first noise signal, so that the amplitude of the noise signal in the received audio signal to be recognized is smaller than that of the first noise signal, active noise reduction of the voice recognition system is realized, and the voice recognition result is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a method of speech recognition provided by one embodiment of the present invention;
fig. 2 is a schematic diagram of an apparatus in which a speech recognition device according to an embodiment of the present invention is located;
FIG. 3 is a schematic diagram of a speech recognition apparatus according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of another speech recognition apparatus provided in accordance with an embodiment of the present invention;
FIG. 5 is a schematic diagram of a speech recognition system provided by one embodiment of the present invention;
fig. 6 is a flow chart of another speech recognition method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a speech recognition method, which may include the following steps:
step 101: receiving a first noise signal sent by an external first acquisition module;
step 102: generating a second noise signal according to the first noise signal;
step 103: sending the second noise signal to an external conversion module so that the conversion module plays a noise reduction audio signal generated according to the second noise signal;
step 104: and receiving the audio signal to be identified sent by the external second acquisition module, and identifying the audio signal to be identified.
In the embodiment of the present invention, the speech recognition method provided in the embodiment of the present invention generates a second noise signal according to the received first noise signal, and the external conversion module plays the noise reduction audio signal generated according to the second noise signal, and recognizes the audio signal to be recognized from the second acquisition module. Therefore, the amplitude of the noise signal obtained by superposing the noise reduction audio signal and the first noise signal is smaller than that of the first noise signal, so that the amplitude of the noise signal in the received audio signal to be recognized is smaller than that of the first noise signal, active noise reduction of the voice recognition system is realized, and the voice recognition result is more accurate.
It should be noted that, in an embodiment of the present invention, the first acquiring module includes a microphone, a first signal amplifier, a first low-pass filter, and a first analog-to-digital converter, where the microphone is configured to convert the acquired first noise into a first noise analog signal, the first signal amplifier is configured to amplify the first noise analog signal, the first low-pass filter is configured to perform low-pass filtering on the first noise analog signal amplified by the first signal amplifier, and output a filtered analog signal, and the first analog-to-digital converter is configured to convert the analog signal filtered by the low-pass filter into the first noise signal. In the embodiment of the invention, the microphone is placed at the position of the main noise source of the target equipment, when the target equipment is started to work, first noise received by the microphone is converted into a first noise signal through the first signal amplifier, the first low-pass filter and the first analog-digital converter in sequence, and the first noise signal is a digital signal.
It is understood that, in the embodiment of the present invention, the target device may be, for example, a household appliance, such as a refrigerator, an air conditioner, an ice chest, or the like, or may be another appliance having the same structure as that provided in the embodiment of the present invention.
It should be noted that, in this embodiment of the present invention, the conversion module includes a FIR filter, a digital-to-analog converter, a second low-pass filter, a power amplifier, and a speaker, where the FIR filter is configured to generate a noise reduction audio signal according to the second noise signal, the digital-to-analog converter is configured to convert the noise reduction audio signal in the digital signal format into the noise reduction audio signal in the analog signal format, the second low-pass filter is configured to perform low-pass filtering on the noise reduction audio signal in the analog signal format, the power amplifier is configured to amplify the filtered noise reduction audio signal, and the speaker is configured to play the noise reduction audio signal amplified by the power amplifier. In the embodiment of the present invention, the second noise signal is converted into the noise reduction audio signal through the FIR filter, the digital-to-analog converter, the second low pass filter, the amplifier, and the speaker in sequence, so as to be played by the speaker, where the second noise signal and the noise reduction audio signal are both digital signals.
It should be noted that, in the embodiment of the present invention, the second acquisition module includes a microphone array, a second signal amplifier, a third low-pass filter, and a second analog-to-data converter, where the microphone array is configured to convert the acquired to-be-identified sound into an analog signal to be identified, the second signal amplifier is configured to amplify the to-be-identified analog signal, the third low-pass filter is configured to perform low-pass filtering on the to-be-identified analog signal, and the second analog-to-data converter is configured to convert the filtered to-be-identified analog signal into an audio signal to be identified. In the embodiment of the invention, the placing position of the microphone array is far away from the position of the main noise source of the target equipment as far as possible, the microphone array receives the sound to be recognized, which contains the sound obtained by superposing the first noise and the noise reduction audio frequency, and also can contain an input voice command, the sound to be recognized received by the microphone array is converted into the audio signal to be recognized through the second signal amplifier, the third low-pass filter and the second analog-data converter in sequence, and the audio signal to be recognized is a digital signal.
It should be further noted that, in the embodiment of the present invention, a time interval between the microphone in the first collection module receiving the first noise and the conversion module playing the noise reduction sound is less than 0.1 second. If the time interval between the first noise and the second noise is less than 0.1 second, the amplitude of the superimposed noise of the first noise and the noise reduction sound collected by the microphone array in the second collection module is less than the amplitude of the first noise, namely the noise collected by the microphone array is the noise superimposed and silenced by the first noise and the noise collected by the microphone array, so that the active noise reduction of the voice recognition system is realized, the noise in the audio signal to be recognized is reduced, and the voice recognition result is more accurate. If the time interval between the first noise and the noise is greater than or equal to 0.1 second, the noise collected by the microphone array in the second collection module includes two sounds, namely the first noise and the noise reduction sound, that is, the noise collected by the microphone array is the noise obtained by superimposing the first noise and the noise reduction sound, so that the noise in the speech recognition system is increased, and therefore the result of the speech recognition is low in accuracy.
In an embodiment of the present invention, based on the speech recognition method shown in fig. 1, the step 102 generates the second noise signal according to the first noise signal, which may specifically include the following steps:
determining a first spectrum of a first noise signal;
generating a second spectrum according to the first spectrum, wherein the second spectrum is opposite to the first spectrum in phase;
and generating a second noise signal according to the second frequency spectrum, wherein the first noise signal and the second noise signal have the same amplitude and opposite phase.
In the embodiment of the present invention, the second spectrum opposite in phase to the first spectrum is generated from the first spectrum of the first noise signal, and the second noise signal identical in amplitude and opposite in phase to the first noise signal is generated from the first spectrum. By the arrangement, the amplitude of the noise signal obtained by superposing the first noise signal and the second noise signal is lower than that of the first noise signal, so that active noise reduction is realized.
It should be noted that, in the embodiment of the present invention, the first noise signal is a digital signal, a first spectrum of the first noise signal is analyzed by using fourier transform, a second spectrum is generated by changing a phase of each frequency in the first spectrum through inverse fourier transform, and a second noise signal having the same amplitude and an opposite phase as those of the first noise signal is output.
In one embodiment of the invention, based on the speech recognition method shown in fig. 1,
the conversion module comprises a FIR filter, wherein the FIR filter is used for generating a noise reduction audio signal according to the second noise signal,
step 104 of identifying the audio signal to be identified includes:
analyzing a third noise signal in the audio signal to be identified;
in the embodiment of the invention, the frequency spectrum of the audio signal to be recognized is analyzed by utilizing Fourier transform, and a third noise signal and a voice signal in the audio signal to be recognized are separated by a voice recognition algorithm, wherein the third noise signal comprises a noise signal generated after the first noise signal and the second noise signal are superposed, and the third noise signal also comprises environmental noise received by a second acquisition module. The separated voice signals can generate voice broadcast signals through the logic part and are finally output through the conversion module, and therefore voice control over the target device is achieved. Because the amplitude of the noise obtained by superposing the first noise signal and the second noise signal in the third noise signal is smaller than that of the first noise signal, the separation speed of the third noise signal and the voice signal in the audio signal to be recognized is high, and the result is more accurate. Therefore, the active noise reduction is adopted, so that the collected voice signals are clearer, the voice recognition capability is improved, and the accuracy of the voice recognition result is improved.
After identifying the audio signal to be identified in step 104, the method further comprises:
and judging whether the third noise signal is converged, if not, determining a third frequency spectrum of the third noise signal, generating a correction coefficient of the FIR filter according to the first frequency spectrum, the second frequency spectrum and the third frequency spectrum, and adjusting the FIR filter by using the correction coefficient.
In the embodiment of the present invention, whether the third noise signal is converged is determined, if not, the third frequency spectrum of the third noise signal is determined, the correction coefficient of the FIR filter is obtained by using the algorithm, and the FIR filter is adjusted by using the obtained correction coefficient, so that the amplitudes of the first noise and the noise reduction sound in the audio signal to be identified received by the second acquisition module are smaller and smaller, that is, the active noise reduction effect can be improved.
It should be noted that, in the embodiment of the present invention, the FIR filter is also called as a finite long single-bit impulse response filter, and is a generic name of a non-recursive filter, the current output sample is only a function of the past and present input samples, and the system impulse response is a finite long sequence, and has a good linear phase, no phase distortion, and good stability. For a fixed set of weight coefficients, the FIR filter output signal is equal to the linearly weighted sum of the elements of the input vector, whereas in practice the weight coefficients are adjustable, the process of adjusting the weight coefficients is called the adaptation process.
It should be noted that, in the embodiment of the present invention, the first frequency spectrum, the second frequency spectrum, and the third frequency spectrum may be calculated by using a Least Mean Square (LMS) algorithm, for example, to generate the correction coefficients of the FIR filter. The LMS algorithm is based on the wiener filtering theory, adopts an algorithm of instantaneous value estimation gradient vector, and updates the weight coefficient of the adaptive filter by minimizing the energy of an error signal. In the embodiment of the present invention, the updated correction coefficient of the filter may be obtained by the following first equation:
the first formula is as follows:
W(n+1)＝W(n)+Ke(n)x(n)
w (n +1) is used to characterize the updated modification coefficient of the FIR filter, W (n) is used to characterize the modification coefficient of the FIR filter, x (n) is used to characterize the input signal to the FIR filter, e (n) is used to characterize the difference between the input signal and the actual signal output according to the input signal, and K is used to characterize the step size coefficient.
As shown in fig. 2 and fig. 3, an embodiment of the present invention provides a speech recognition apparatus. The embodiment of the speech recognition device can be implemented by software, or by hardware, or by a combination of hardware and software. From a hardware level, as shown in fig. 2, a hardware structure diagram of a device in which a speech recognition apparatus according to an embodiment of the present invention is located is provided, where the device in the embodiment may generally include other hardware, such as a forwarding chip responsible for processing a packet, in addition to the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 2. Taking a software implementation as an example, as shown in fig. 3, as a logical apparatus, the apparatus is formed by reading, by a CPU of a device in which the apparatus is located, corresponding computer program instructions in a non-volatile memory into a memory for execution.
As shown in fig. 3, an embodiment of the present invention provides a speech recognition apparatus, including: a processing unit 301, a transmitting unit 302 and a recognizing unit 303;
the processing unit 301 is configured to receive a first noise signal sent by an external first acquisition module, and generate a second noise signal according to the first noise signal;
a sending unit 302, configured to send the second noise signal generated by the processing unit 301 to an external conversion module, so that the conversion module plays a noise reduction audio signal generated according to the second noise signal, where an amplitude of a noise signal obtained by superimposing the noise reduction audio signal and the first noise signal is smaller than an amplitude of the first noise signal;
the identifying unit 303 is configured to receive an audio signal to be identified sent by an external second acquisition module, and identify the audio signal to be identified, where the audio signal to be identified includes a noise signal obtained by superimposing the first noise signal and the noise reduction audio signal.
In one embodiment of the invention, based on the speech recognition device shown in fig. 3,
a processing unit 301 for performing the following processing:
determining a first spectrum of a first noise signal;
generating a second spectrum according to the first spectrum, wherein the second spectrum is opposite to the first spectrum in phase;
and generating a second noise signal according to the second frequency spectrum, wherein the first noise signal and the second noise signal have the same amplitude and opposite phase.
In one embodiment of the invention, based on the speech recognition device shown in fig. 3,
the conversion module comprises an FIR filter, wherein the FIR filter is used for generating a noise reduction audio signal according to the second noise signal;
the identifying unit 303 is configured to analyze a third noise signal in the audio signal to be identified;
as shown in fig. 4, the speech recognition apparatus further includes: an adjustment unit 401;
an adjusting unit 401, configured to determine whether the third noise signal analyzed by the identifying unit 303 converges, if the third noise signal does not converge, determine a third frequency spectrum of the third noise signal, generate a correction coefficient of the FIR filter according to the first frequency spectrum, the second frequency spectrum, and the third frequency spectrum, and adjust the FIR filter by using the correction coefficient.
As shown in fig. 5, one embodiment of the present invention provides a speech recognition system, including: the voice recognition device 501, the first acquisition module 502, the conversion module 503 and the second acquisition module 504 provided in any of the above embodiments;
a first collecting module 502, configured to collect a first noise signal and send the first noise signal to the speech recognition device 501;
a conversion module 503, configured to receive the second noise signal sent from the speech recognition device 501, generate a noise reduction audio signal according to the second noise signal, and play the noise reduction audio signal, where an amplitude of a noise signal obtained by superimposing the noise reduction audio signal and the first noise signal is smaller than an amplitude of the first noise signal;
the second collecting module 504 is configured to collect an audio signal to be recognized, and send the audio signal to be recognized to the speech recognition device 501, where the audio signal to be recognized includes a noise signal obtained by superimposing the first noise signal and the noise reduction audio signal.
In one embodiment of the invention, based on the speech recognition system shown in fig. 5,
when the voice recognition system is deployed on the target device, the distance between the first acquisition module 502 and a target part of the target device, which generates noise, is smaller than a preset value;
the first acquisition module 502 is configured to perform noise acquisition on a target portion to obtain a first noise signal, where the first noise signal includes noise emitted by the target portion;
the first acquisition module 502 includes: a microphone, a first signal amplifier, a first low-pass filter and a first analog-to-digital converter,
the microphone is used for converting the collected first noise into a first noise analog signal;
the first signal amplifier is used for amplifying the first noise analog signal;
the first low-pass filter is used for performing low-pass filtering on the first noise analog signal amplified by the first signal amplifier and outputting a filtered analog signal;
the first analog-digital converter is used for converting the analog signal filtered by the low-pass filter into a first noise signal, and the first noise signal is a digital signal;
the conversion module 503 includes: an FIR filter, a digital-to-analog converter, a second low pass filter, a power amplifier and a loudspeaker,
the FIR filter is used for generating a noise reduction audio signal according to a second noise signal, and the second noise signal and the noise reduction audio signal are both digital signals;
the digital-to-analog converter is used for converting the noise reduction audio signal in the digital signal format into the noise reduction audio signal in the analog signal format;
the second low-pass filter is used for carrying out low-pass filtering on the noise reduction audio signal in the analog signal format;
the power amplifier is used for amplifying the filtered noise reduction audio signal;
the loudspeaker is used for playing the noise reduction audio signal amplified by the power amplifier;
the second acquisition module 504 includes: a microphone array, a second signal amplifier, a third low-pass filter and a second analog-to-data converter,
the microphone array is used for converting collected to-be-identified sound into to-be-identified analog signals;
the second signal amplifier is used for amplifying the analog signal to be identified;
the third low-pass filter is used for performing low-pass filtering on the analog signal to be identified;
the second analog-data converter is used for converting the filtered analog signal to be identified into the audio signal to be identified, and the audio signal to be identified is a digital signal.
It should be noted that, in the embodiment of the present invention, the target device may be, for example, a household appliance, such as a refrigerator, an air conditioner, an ice chest, or the like, or may be another appliance having the same structure as that provided in the embodiment of the present invention. For example, when the target device is a refrigerator, the first acquisition module is deployed at a position as close as possible to a main noise source of the refrigerator, and after the refrigerator is started to work, a first noise signal acquired by a microphone in the first acquisition module is mainly noise emitted by the main noise source of the refrigerator. The voice recognition device generates a noise reduction audio signal which has the same amplitude as the first noise signal but is opposite in phase, the noise reduction audio signal is played by the loudspeaker, noise reduction sound played by the loudspeaker and noise emitted by main noise of the refrigerator can be mutually offset after being mixed, noise with the amplitude smaller than the first noise signal is generated, and active noise reduction is achieved. In addition, the microphone array in the second acquisition module can be used for acquiring an input voice command and also can be used as a monitoring microphone for acquiring noise signals obtained by mixing noise reduction sound played by the loudspeaker and noise emitted by main noise of the refrigerator, and the FIR filter is adjusted according to the mixed noise signals through the voice recognition device, so that the second acquisition module is deployed at a position far away from the main noise source of the refrigerator as far as possible, errors caused by the fact that the microphone array acquires the first noise signals are avoided, and the active noise reduction effect of the voice recognition system is favorably improved.
The configuration illustrated in the embodiment of the present invention is not intended to specifically limit the speech recognition apparatus. In other embodiments of the invention, the speech recognition apparatus may include more or fewer components than shown, or some components may be combined, some components may be split, or a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
Because the content of information interaction, execution process, and the like among the modules in the device is based on the same concept as the method embodiment of the present invention, specific content can be referred to the description in the method embodiment of the present invention, and is not described herein again.
The following describes the speech recognition method provided by the embodiment of the present invention in further detail with reference to the speech recognition system shown in fig. 5, and as shown in fig. 6, the method may include the following steps:
step 601: the first acquisition module acquires a first noise signal and sends the first noise signal to the voice recognition device.
In the embodiment of the invention, the first noise signal is a digital signal, the first acquisition module comprises a microphone, a first signal amplifier, a first low-pass filter and a first analog-digital converter, the microphone is arranged at the position of a main noise source of the target equipment, and after the target equipment is started to work, the microphone converts the received first noise into a first noise signal through the first signal amplifier, the first low-pass filter and the first analog-digital converter and sends the first noise signal to the voice recognition device.
Step 602: the speech recognition device determines a first spectrum of a first noise signal.
In this step, after receiving the first noise signal from the first acquisition module, the speech recognition device analyzes a first frequency spectrum of the first noise signal by using fourier transform.
Step 603: the speech recognition device generates a second noise signal.
In the step, after determining a first frequency spectrum of a first noise signal, the voice recognition device generates a second frequency spectrum by changing the phase of each frequency in the first frequency spectrum through inverse Fourier transform, and generates a second noise signal which has the same amplitude and opposite phase with the first noise signal according to the second frequency spectrum, wherein the second noise signal is a digital signal.
Step 604: the conversion module plays the noise reduction audio signal generated according to the second noise signal.
In an embodiment of the present invention, the conversion module includes an FIR filter, a digital-to-analog converter, a second low-pass filter, a power amplifier, and a speaker, after the voice recognition device outputs the generated second noise signal, the second noise signal is converted into a noise reduction audio signal through the FIR filter, the digital-to-analog converter, the second low-pass filter, the power amplifier, and the speaker in sequence, and is played by the speaker, where the noise reduction audio signal is a digital signal.
Step 605: the second acquisition module acquires an audio signal to be recognized and sends a second noise signal to the voice recognition device.
In the embodiment of the invention, the second acquisition module comprises a microphone array, a second signal amplifier, a third low-pass filter and a second analog-to-data converter, the microphone array is placed at a position as far as possible away from a main noise source of the target device, the microphone array receives the sound to be recognized, which contains the superposed sound of the first noise and the noise reduction sound, and also contains the input voice command and the environmental noise of the environment where the sound is located, and the superposed sound of the first noise and the noise reduction sound is lower than the first noise. And converting the sound to be identified received by the microphone array into an audio signal to be identified through a second signal amplifier, a third low-pass filter and a second analog-data converter, and sending the audio signal to be identified to the voice identification device, wherein the audio signal to be identified is a digital signal.
Step 606: the speech recognition device analyzes a third noise signal in the audio signal to be recognized.
In this step, after the voice recognition device receives the audio signal to be recognized from the second acquisition module, the frequency spectrum of the audio signal to be recognized is analyzed by utilizing fourier transform, and a third noise signal and a voice signal in the audio signal to be recognized are separated by a voice recognition algorithm, wherein the third noise signal comprises a noise signal generated after the first noise signal and the second noise signal are superposed, the noise environment received by the second acquisition module can also be included, the separated voice signal can generate a voice broadcast signal through a logic part, and the voice broadcast signal is finally output through the conversion module, so that the voice control of the target device is realized.
Step 607: the speech recognition device determines whether the third noise signal is converged, if not, step 608 is executed, otherwise, the current process is ended.
In this step, the speech recognition apparatus determines whether the third noise signal converges, wherein the convergence may be, for example, a convergence within a predetermined threshold range, if not, step 608 is executed, otherwise, the current flow is ended.
Step 608: the speech recognition apparatus adjusts the correction coefficient of the FIR filter.
In this step, the speech recognition apparatus may generate an update correction coefficient of the FIR filter according to the first spectrum, the second spectrum, and the third spectrum, and adjust the FIR filter by using the update correction coefficient, specifically, the update correction coefficient of the FIR filter may be generated by the following first equation:
the first formula is as follows:
W(n+1)＝W(n)+Ke(n)x(n)
w (n +1) is used to characterize the updated modification coefficient of the FIR filter, W (n) is used to characterize the modification coefficient of the FIR filter, x (n) is used to characterize the input signal to the FIR filter, e (n) is used to characterize the difference between the input signal and the actual signal output according to the input signal, and K is used to characterize the step size coefficient.
An embodiment of the present invention further provides an intelligent device, including: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor is configured to invoke the machine readable program to perform the speech recognition method of any embodiment of the present invention.
Embodiments of the present invention further provide a computer-readable medium, where computer instructions are stored, and when executed by a processor, cause the processor to execute a speech recognition method in any embodiment of the present invention.
In this case, the program code itself read from the storage medium can realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.
Examples of the storage medium for supplying the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer via a communications network.
Further, it should be clear that the functions of any one of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform a part or all of the actual operations based on instructions of the program code.
Further, it is to be understood that the program code read out from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion module connected to the computer, and then causes a CPU or the like mounted on the expansion board or the expansion module to perform part or all of the actual operations based on instructions of the program code, thereby realizing the functions of any of the above-described embodiments.
It should be noted that not all steps and units in the above flows and system structure diagrams are necessary, and some steps or units may be omitted according to actual needs. The execution order of the steps is not fixed and can be adjusted as required. The system structures described in the above embodiments may be physical structures or logical structures, that is, some units may be implemented by the same physical entity, or some units may be implemented by a plurality of physical entities, or some units may be implemented by some components in a plurality of independent devices.
In the above embodiments, the hardware module may be implemented mechanically or electrically. For example, a hardware module may comprise permanently dedicated circuitry or logic (such as a dedicated processor, FPGA or ASIC) to perform the corresponding operations. A hardware module may also include programmable logic or circuitry (e.g., a general-purpose processor or other programmable processor) that may be temporarily configured by software to perform the corresponding operations. The specific implementation (mechanical, or dedicated permanent, or temporarily set) may be determined based on cost and time considerations.
While the invention has been shown and described in detail in the drawings and in the preferred embodiments, it is not intended to limit the invention to the embodiments disclosed, and it will be apparent to those skilled in the art that various combinations of the code auditing means in the various embodiments described above may be used to obtain further embodiments of the invention, which are also within the scope of the invention.
Claims (10)
1. A speech recognition method, comprising:
receiving a first noise signal sent by an external first acquisition module;
generating a second noise signal according to the first noise signal;
sending the second noise signal to an external conversion module so that the conversion module plays a noise reduction audio signal generated according to the second noise signal, wherein the amplitude of a noise signal obtained by superposing the noise reduction audio signal and the first noise signal is smaller than that of the first noise signal;
and receiving an audio signal to be identified sent by an external second acquisition module, and identifying the audio signal to be identified, wherein the audio signal to be identified comprises a noise signal obtained by superposing the first noise signal and the noise reduction audio signal.
2. The method of claim 1,
generating a second noise signal from the first noise signal, comprising:
determining a first spectrum of the first noise signal;
generating a second spectrum from the first spectrum, wherein the second spectrum is in phase opposition to the first spectrum;
and generating the second noise signal according to the second frequency spectrum, wherein the first noise signal and the second noise signal have the same amplitude and the opposite phase.
3. The method of claim 2,
the conversion module comprises an FIR filter;
the FIR filter is used for generating the noise reduction audio signal according to the second noise signal;
the identifying the audio signal to be identified includes:
analyzing a third noise signal in the audio signal to be identified;
after the identifying the audio signal to be identified, further comprising:
and judging whether the third noise signal is converged, if not, determining a third frequency spectrum of the third noise signal, generating a correction coefficient of the FIR filter according to the first frequency spectrum, the second frequency spectrum and the third frequency spectrum, and adjusting the FIR filter by using the correction coefficient.
4. A speech recognition apparatus, comprising: a processing unit, a sending unit and a recognition unit;
the processing unit is used for receiving a first noise signal sent by an external first acquisition module and generating a second noise signal according to the first noise signal;
the transmitting unit is configured to transmit the second noise signal generated by the processing unit to an external conversion module, so that the conversion module plays a noise reduction audio signal generated according to the second noise signal, where an amplitude of a noise signal obtained by superimposing the noise reduction audio signal and the first noise signal is smaller than an amplitude of the first noise signal;
the identification unit is used for receiving an audio signal to be identified sent by an external second acquisition module and identifying the audio signal to be identified, wherein the audio signal to be identified comprises a noise signal obtained by superposing the first noise signal and the noise reduction audio signal.
5. The apparatus of claim 4,
the processing unit is used for executing the following processing:
determining a first spectrum of the first noise signal;
generating a second spectrum from the first spectrum, wherein the second spectrum is in phase opposition to the first spectrum;
and generating the second noise signal according to the second frequency spectrum, wherein the first noise signal and the second noise signal have the same amplitude and the opposite phase.
6. The apparatus of claim 5,
the conversion module comprises an FIR filter, wherein the FIR filter is used for generating the noise reduction audio signal according to the second noise signal;
the identification unit is used for analyzing a third noise signal in the audio signal to be identified;
further comprising: an adjustment unit;
the adjusting unit is configured to determine whether the third noise signal analyzed by the identifying unit converges, determine a third frequency spectrum of the third noise signal if the third noise signal does not converge, generate a correction coefficient of the FIR filter according to the first frequency spectrum, the second frequency spectrum, and the third frequency spectrum, and adjust the FIR filter by using the correction coefficient.
7. A speech recognition system, comprising: the speech recognition device of any one of claims 4 to 6, the first acquisition module, the conversion module, and the second acquisition module;
the first acquisition module is used for acquiring a first noise signal and sending the first noise signal to the voice recognition device;
the conversion module is configured to receive a second noise signal sent by the speech recognition device, generate a noise reduction audio signal according to the second noise signal, and play the noise reduction audio signal, where an amplitude of a noise signal obtained by superimposing the noise reduction audio signal and the first noise signal is smaller than an amplitude of the first noise signal;
the second acquisition module is used for acquiring an audio signal to be identified and sending the audio signal to be identified to the voice recognition device, wherein the audio signal to be identified comprises the noise signal obtained by superposing the first noise signal and the noise reduction audio signal.
8. The system of claim 7,
when the voice recognition system is deployed on target equipment, the distance between the first acquisition module and a target part of the target equipment, which emits noise, is smaller than a preset value;
the first acquisition module is used for carrying out noise acquisition on the target part to obtain the first noise signal, wherein the first noise signal comprises noise emitted by the target part;
and/or the presence of a gas in the gas,
the first acquisition module comprises: a microphone, a first signal amplifier, a first low-pass filter and a first analog-to-digital converter,
wherein the microphone is used for converting the collected first noise into a first noise analog signal;
the first signal amplifier is used for amplifying the first noise analog signal;
the first low-pass filter is used for performing low-pass filtering on the first noise analog signal amplified by the first signal amplifier and outputting a filtered analog signal;
the first analog-to-digital converter is configured to convert the analog signal filtered by the low-pass filter into the first noise signal, where the first noise signal is a digital signal;
and/or the presence of a gas in the gas,
the conversion module includes: an FIR filter, a digital-to-analog converter, a second low pass filter, a power amplifier and a loudspeaker,
wherein the FIR filter is configured to generate the noise reduction audio signal according to the second noise signal, and both the second noise signal and the noise reduction audio signal are digital signals;
the digital-to-analog converter is used for converting the noise reduction audio signal in the digital signal format into the noise reduction audio signal in the analog signal format;
the second low-pass filter is used for low-pass filtering the noise reduction audio signal in the analog signal format;
the power amplifier is used for amplifying the filtered noise reduction audio signal;
the loudspeaker is used for playing the noise reduction audio signal amplified by the power amplifier;
and/or the presence of a gas in the gas,
the second acquisition module comprises: a microphone array, a second signal amplifier, a third low-pass filter and a second analog-to-data converter,
the microphone array is used for converting collected sounds to be identified into analog signals to be identified;
the second signal amplifier is used for amplifying the analog signal to be identified;
the third low-pass filter is used for performing low-pass filtering on the analog signal to be identified;
the second analog-to-data converter is used for converting the filtered analog signal to be identified into an audio signal to be identified, and the audio signal to be identified is a digital signal.
9. Smart device, characterized in that it comprises: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor, configured to invoke the machine readable program to perform the speech recognition method of any of claims 1 to 3.
10. Computer readable medium, characterized in that it has stored thereon computer instructions which, when executed by a processor, cause the processor to carry out the speech recognition method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010911281.1A CN112133297A (en) | 2020-09-02 | 2020-09-02 | Voice recognition method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010911281.1A CN112133297A (en) | 2020-09-02 | 2020-09-02 | Voice recognition method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112133297A true CN112133297A (en) | 2020-12-25 |
Family
ID=73848475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010911281.1A Pending CN112133297A (en) | 2020-09-02 | 2020-09-02 | Voice recognition method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112133297A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105405438A (en) * | 2014-09-10 | 2016-03-16 | 哈曼贝克自动系统股份有限公司 | Adaptive noise control system with improved robustness |
| CN206225001U (en) * | 2016-07-27 | 2017-06-06 | 歌尔股份有限公司 | Intelligent sound equipment |
| CN108737772A (en) * | 2017-04-13 | 2018-11-02 | 广东美的智美科技有限公司 | Range hood and interaction noise-reduction method |
| CN108766458A (en) * | 2018-07-05 | 2018-11-06 | 浙江众邦机电科技有限公司 | A kind of industrial sewing machine noise-reduction method, device and equipment based on noise |
| US20200001469A1 (en) * | 2019-08-07 | 2020-01-02 | Lg Electronics Inc. | Robot |
-
2020
- 2020-09-02 CN CN202010911281.1A patent/CN112133297A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105405438A (en) * | 2014-09-10 | 2016-03-16 | 哈曼贝克自动系统股份有限公司 | Adaptive noise control system with improved robustness |
| CN206225001U (en) * | 2016-07-27 | 2017-06-06 | 歌尔股份有限公司 | Intelligent sound equipment |
| CN108737772A (en) * | 2017-04-13 | 2018-11-02 | 广东美的智美科技有限公司 | Range hood and interaction noise-reduction method |
| CN108766458A (en) * | 2018-07-05 | 2018-11-06 | 浙江众邦机电科技有限公司 | A kind of industrial sewing machine noise-reduction method, device and equipment based on noise |
| US20200001469A1 (en) * | 2019-08-07 | 2020-01-02 | Lg Electronics Inc. | Robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112447191B (en) | Signal processing device and signal processing method | |
| CN101924525B (en) | High performance voice frequency amplifying circuit | |
| US7756280B2 (en) | Audio processing system and method for automatically adjusting volume | |
| US20110051953A1 (en) | Calibrating multiple microphones | |
| WO2008091403A1 (en) | System and method for calibrating phase and gain mismatches of an array microphone | |
| JP4848151B2 (en) | Sound field measuring apparatus and sound field measuring method | |
| CN102194451A (en) | Signal processing device and stringed instrument | |
| CN113490115A (en) | Acoustic feedback suppression method and system based on voiceprint recognition technology | |
| CN112509595A (en) | Audio data processing method, system and storage medium | |
| JP5975290B2 (en) | Howling suppression device, hearing aid, howling suppression method, and integrated circuit | |
| JPH08228396A (en) | Sound reproducing device | |
| CN110876106A (en) | Electronic device, noise reduction method, computer system, and medium | |
| KR100765793B1 (en) | Apparatus and method of equalizing room parameter for audio system with acoustic transducer array | |
| CN112133297A (en) | Voice recognition method, device and system | |
| JP2004012151A (en) | System of estimating direction of sound source | |
| CN113223544A (en) | Audio direction positioning detection device and method and audio processing system | |
| EP2259607A1 (en) | Data relay apparatus, acoustic reproduction system and control method of the same | |
| JP2000250577A (en) | Voice recognition device and learning method and learning device to be used in the same device and recording medium on which the same method is programmed and recorded | |
| CN110610714B (en) | Audio signal enhancement processing method and related device | |
| JP2015070292A (en) | Sound collection/emission device and sound collection/emission program | |
| CN104254041A (en) | Near-end listening intelligibility enhancement | |
| CN109831707B (en) | Sound effect parameter setting method, sound effect acquisition effector and musical instrument system | |
| CN113573205B (en) | Signal processing method, apparatus and computer storage medium | |
| JP3489589B2 (en) | Noise reduction device | |
| CN117238267A (en) | Noise reduction method, equipment, dish washer and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201225 |