CN112562713A - Sound processing method, sound processing device, electronic device, and medium - Google Patents
Sound processing method, sound processing device, electronic device, and medium Download PDFInfo
- Publication number
- CN112562713A CN112562713A CN201910922365.2A CN201910922365A CN112562713A CN 112562713 A CN112562713 A CN 112562713A CN 201910922365 A CN201910922365 A CN 201910922365A CN 112562713 A CN112562713 A CN 112562713A
- Authority
- CN
- China
- Prior art keywords
- data
- noise reduction
- sound
- noise
- sound data
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 230000009467 reduction Effects 0.000 claims abstract description 135
- 230000007613 environmental effect Effects 0.000 claims abstract description 50
- 238000000034 method Methods 0.000 claims description 34
- 230000009471 action Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 19
- 238000004590 computer program Methods 0.000 description 11
- 230000000875 corresponding effect Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000010408 sweeping Methods 0.000 description 5
- 102100022002 CD59 glycoprotein Human genes 0.000 description 2
- 101000897400 Homo sapiens CD59 glycoprotein Proteins 0.000 description 2
- 101001121074 Homo sapiens MICOS complex subunit MIC13 Proteins 0.000 description 2
- 102100026627 MICOS complex subunit MIC13 Human genes 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 238000011946 reduction process Methods 0.000 description 2
- 239000000758 substrate Substances 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000018044 dehydration Effects 0.000 description 1
- 238000006297 dehydration reaction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques 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
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Circuit For Audible Band Transducer (AREA)
- Soundproofing, Sound Blocking, And Sound Damping (AREA)
Abstract
The present disclosure provides a sound processing method for processing environmental sound acquired by an electronic device, including: pre-storing first sound data and a preset noise angle of the electronic equipment in all directions during working; acquiring environmental sound data of the electronic equipment during working, and performing noise reduction processing on the environmental sound data according to the first sound data to obtain first noise reduction data; removing data which accord with a preset noise angle in the first noise reduction data to obtain second noise reduction data; and performing voice recognition on the second noise reduction data. Under the condition that the frequency of the second sound data is larger than a preset threshold value, carrying out noise reduction processing on the first noise reduction data according to the second sound data to obtain third noise reduction data; and removing the data which accord with the preset noise angle in the third noise reduction data to obtain second noise reduction data. The present disclosure also provides a sound processing apparatus, an electronic device, and a computer-readable storage medium.
Description
Technical Field
The present disclosure relates to the field of speech recognition, and in particular, to a sound processing method and apparatus, an electronic device, and a medium.
Background
With the gradual development of artificial intelligence, more and more electronic devices can be controlled through a man-machine interaction mode. In the actual working environment of the electronic equipment, various noises exist, the interference of the noises has great influence on the recognition of the voice command, and the higher the noises are, the lower the accuracy of the voice recognition is. For example, because speech recognition is seriously affected by self working noise (various motor rotation sounds), the recognition effect of the intelligent sweeping robot which is widely used at present is poor, and the intelligent sweeping robot cannot accurately recognize a speech instruction, so that the normal work of the intelligent sweeping robot is affected.
Disclosure of Invention
According to a first aspect of the embodiments of the present disclosure, there is provided a sound processing method for processing an environmental sound acquired by an electronic device, including: prestoring first sound data and a preset noise angle of the electronic equipment in all directions during working; acquiring environmental sound data of the electronic equipment during working, and performing noise reduction processing on the environmental sound data according to the first sound data to obtain first noise reduction data; removing data which accord with the preset noise angle in the first noise reduction data to obtain second noise reduction data; and performing voice recognition on the second noise reduction data.
Optionally, when obtaining the environmental sound data of the electronic device during operation, further obtaining second sound data generated by the electronic device at a fixed location, where, when a frequency of the second sound data is greater than a preset threshold, removing data that meets the predetermined noise angle from the first noise reduction data to obtain second noise reduction data includes: performing noise reduction processing on the first noise reduction data according to the second sound data to obtain third noise reduction data; and removing the data which accords with the preset noise angle in the third noise reduction data to obtain the second noise reduction data.
Optionally, the performing noise reduction processing on the environmental sound data according to the first sound data includes: setting a first weight factor for the first sound data; calculating the first sound data and the first weight factor to obtain first weighted noise data; and calculating the ambient sound data and the first weighted noise data to obtain the first noise reduction data.
Optionally, the performing noise reduction processing on the first noise reduction data according to the second sound data to obtain third noise reduction data includes: setting a second weighting factor for the second sound data; calculating the second sound data and the second weighting factor to obtain second weighted noise data; and calculating the first noise reduction data and the second weighted noise data to obtain the third noise reduction data.
Optionally, the acquiring the environmental sound data of the electronic device during operation includes: and filtering data with the frequency higher than the preset frequency in the environmental sound data.
Optionally, the first sound data is multiplied by the first weighting factor, and the second sound data is multiplied by the second weighting factor; the ambient sound data and the first weighted noise data are subtracted from each other, and the ambient sound data and the second weighted noise data are subtracted from each other.
Optionally, the preset frequency is set to a human voice frequency.
According to a second aspect of embodiments of the present disclosure, there is provided an electronic apparatus including: the system comprises a sound acquisition array, a sound processing unit and a sound processing unit, wherein each unit of the sound acquisition array comprises a first sound acquisition unit and a second sound acquisition unit, the first sound acquisition unit is used for acquiring first sound data of the electronic equipment in all directions during working and environment sound data of the electronic equipment during working, and the second sound acquisition unit is used for acquiring second sound data generated by the electronic equipment at a fixed position; the first processing unit is used for carrying out noise reduction processing on the environmental sound data according to the first sound data to obtain first noise reduction data; the second processing unit is used for removing the data which accord with the preset noise angle in the first noise reduction data to obtain second noise reduction data; a voice recognition unit, configured to perform voice recognition on the second noise reduction data to obtain a control instruction; and the control unit is used for controlling the action of the electronic equipment according to the control command.
Optionally, the electronic device further includes: and the third processing unit is used for performing noise reduction processing on the first noise reduction data according to the second sound data to obtain third noise reduction data under the condition that the second sound data is larger than a preset threshold value, and then removing data which accord with the preset noise angle in the third noise reduction data to obtain the second noise reduction data.
Optionally, the electronic device further includes: and the low-pass filter circuit is used for filtering data with the frequency higher than the preset frequency in the environmental sound data.
Optionally, the sound collection array is provided with an independent power supply.
According to a third aspect of the embodiments of the present disclosure, there is provided a sound processing apparatus for processing an environmental sound acquired by an electronic device, the apparatus including: the pre-storage module is used for pre-storing the omnidirectional first sound data and the preset noise angle when the electronic equipment works; the acquisition module is used for acquiring environmental sound data of the electronic equipment during working; the first processing module is used for carrying out noise reduction processing on the environmental sound data according to the first sound data to obtain first noise reduction data; the second processing module is used for removing data which accord with the preset noise angle in the first noise reduction data to obtain second noise reduction data; and the voice recognition module is used for carrying out voice recognition on the second noise reduction data.
According to a fourth aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including: one or more processors. Memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method as described above.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium storing computer-executable instructions for implementing the method as described above when executed.
According to a sixth aspect of embodiments of the present disclosure, there is provided a computer program comprising computer executable instructions for implementing the method as described above when executed.
According to the sound processing method, the sound processing device, the electronic equipment and the medium, not only is the primary noise reduction of the environmental sound including the voice command performed based on the acquired omnibearing motor noise data when the electronic equipment works, and a part of motor noise is removed, but also the further noise reduction of the environmental sound is performed based on the acquired noise data of the electronic equipment in the fixed angle direction, and meanwhile, the noise is suppressed based on the motor noise angle, and then the motor noise is further removed, so that the accuracy of the voice recognition of the electronic equipment is improved.
Drawings
For a more complete understanding of the present disclosure and the advantages thereof, reference is now made to the following descriptions taken in conjunction with the accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description serve to explain the principles of the invention. Wherein:
FIG. 1 is a system architecture diagram illustrating a sound processing method and apparatus according to an exemplary embodiment;
FIG. 2 is a flow diagram illustrating a sound processing method according to an exemplary embodiment;
FIG. 3 is a flow diagram illustrating a sound processing method according to an exemplary embodiment;
FIG. 4 is a block diagram illustrating an electronic device in accordance with an exemplary embodiment;
FIG. 5 is a diagram illustrating a sound collection array architecture for an electronic device in accordance with an exemplary embodiment;
FIG. 6 is a diagram illustrating a sound collection array structure of an electronic device with a low pass filter in accordance with one exemplary embodiment;
FIG. 7 is a circuit block diagram of an electronic device shown in accordance with an exemplary embodiment
FIG. 8 is a block diagram illustrating a sound processing device according to an exemplary embodiment; and
FIG. 9 is a block diagram illustrating an electronic device in accordance with an example embodiment.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The embodiment of the disclosure provides a sound processing method, and an electronic device and a sound processing apparatus which can apply the method. The method comprises the step of prestoring first sound data and a preset noise angle of the electronic equipment in all directions during working. The method comprises the steps of obtaining environmental sound data of the electronic equipment during working, and conducting noise reduction processing on the environmental sound data according to the first sound data to obtain first noise reduction data. And removing the data which accord with the preset noise angle in the first noise reduction data to obtain second noise reduction data. And performing voice recognition on the second noise reduction data.
Fig. 1 is a system architecture diagram 100 illustrating a sound processing method and apparatus according to an example embodiment. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.
As shown in fig. 1, the system architecture 100 according to the embodiment may include, for example, a voice instruction generator 101 and an electronic device 102.
The voice instruction generator 101 may be, for example, an actual person, or a device that can transmit a voice instruction. The electronic device 102 may be, for example, an intelligent sweeping robot, an intelligent refrigerator, an intelligent washing machine, or the like. According to the embodiment of the disclosure, the voice instruction generator 101 sends a voice instruction according to an actual requirement, for example, garbage on the left of the intelligent sweeping robot needs to be cleaned, and the voice instruction generator 101 sends a voice instruction for controlling the intelligent robot to move left. The electronic device 102 receives the environmental sound through the voice receiving device installed thereon, and the environmental sound includes the noise generated when the electronic device 102 itself operates and other environmental noises in addition to the voice instruction. The electronic device 102 may perform noise reduction processing on the environmental sound according to the sound processing method of the embodiment of the present disclosure, so that the electronic device 102 can accurately recognize speech intelligence to perform corresponding actions.
FIG. 2 is a flow diagram illustrating a sound processing method according to an example embodiment.
As shown in fig. 2, the sound processing method according to the embodiment of the disclosure may be used to process the environmental sound acquired by the electronic device, and the method may include operations S201 to S204, for example.
In operation S201, first sound data and a predetermined noise angle of an omni-bearing environment when the electronic device is in operation are pre-stored.
Since it is difficult to receive only a pure voice command in an actual operation process, the pure voice command generally includes noise generated by the electronic device itself, such as a sound generated when an engine of the electronic device operates, and other noise generated by some animals when a human sends a voice command. These sounds can affect the accuracy of speech recognition. Since the noise generated by the electronic device itself is generated continuously while the electronic device is operating, and other noise of the surrounding environment is generally generated occasionally, the noise generated by the electronic device itself generally has a higher influence on the speech recognition than other noise of the surrounding environment. The influence of noise generated by the electronic equipment on the speech recognition can be eliminated in the embodiment of the disclosure.
The voice command may be generated at any position of the electronic device, and in order to accurately receive the voice command, the electronic device generally employs an omnidirectional sound receiving device, such as an omnidirectional microphone. When the voice command is acquired in all directions, in addition to the voice command generated by the voice command and transmitted from the direction, echo returned by the voice command through the obstacle can be acquired, and the same is true for noise data. Therefore, in order to obtain a good noise reduction effect, the same voice acquisition device (omni-directional microphone) is generally used to acquire noise data to reduce the noise of the ambient sound. Specifically, under the condition that the surrounding environment is quiet, omni-directional microphones can be used to collect all-directional first sound data (for example, omni-directional microphone collection) generated by the motor when the electronic device is working, and the first sound data mainly comprises noise data generated by the motor when the electronic device is working. Based on the first sound data, a noise source can be positioned, and a motor noise angle can be determined. And storing the acquired first sound data and the acquired noise angle, so that the first sound data and the noise angle can be directly read in the subsequent electronic equipment working engineering, and the noise reduction processing can be performed on the acquired environmental sound containing the voice command.
In operation S202, ambient sound data of the electronic device during operation is obtained, and noise reduction processing is performed on the ambient sound data according to the first sound data, so as to obtain first noise reduction data.
When a voice instruction is sent out by a person, the electronic equipment acquires the environmental sound comprising the voice instruction through the sound acquisition device. At this time, the electronic device can read the pre-stored first sound data, and perform noise reduction processing on the ambient sound to remove noise data, which is included in the ambient sound and generated by the motor when the electronic device works, acquired in an all-dimensional manner, so as to obtain first noise reduction data.
Specifically, first, a first weighting factor is set for the first sound data, and the first weighting factor may be adjusted according to the actual recognition effect, which is not limited in the present invention. And secondly, performing multiplication operation on the first sound data and the first weight factor to obtain first weighted noise data. And finally, subtracting the ambient sound data and the first weighted noise data to remove part of noise data to obtain first noise reduction data.
The noise reduction process is a preliminary noise reduction process, and the first noise reduction data also comprises motor noise data of part of the electronic equipment.
In addition, because the voice command is generally a voice command, which is an effective command, and the noise frequency of the motor of the electronic device is higher and obviously higher than the frequency of normal voice, when the environmental sound data is acquired, the data with the frequency higher than the preset frequency in the environmental sound data can be filtered out firstly. The preset frequency may be, for example, a human voice frequency.
In operation S203, data corresponding to a predetermined noise angle in the first noise reduction data is removed to obtain second noise reduction data.
In order to be able to further remove the motor noise data remaining in the first noise data, a pre-stored noise angle, i.e. the orientation of the motor, may be read. The noise of the azimuth is suppressed, and the motor noise in the first noise reduction data can be further removed.
In operation S204, speech recognition is performed on the second noise reduction data.
Due to the noise reduction processing in operations S202 to S203, the motor noise data in the environmental sound is greatly reduced, and the electronic device can accurately recognize the contents of the voice command, such as left movement, right movement, door opening, dehydration, and the like, and execute corresponding actions according to the contents.
In this embodiment, based on the electronic equipment during operation all-round motor noise data that acquire tentatively fall making an uproar to the environment sound including voice command, get rid of partly motor noise, simultaneously, restrain the noise based on motor noise angle, further get rid of motor noise, gain good noise reduction effect to improve speech recognition's rate of accuracy.
FIG. 3 is a flow diagram illustrating a sound processing method according to an example embodiment.
As shown in fig. 3, the sound processing method of the embodiment of the present disclosure may be used to process an environmental sound acquired by an electronic device. Compared with the sound processing method in the above embodiment, the present embodiment adds a process of reducing noise of the environmental sound based on the second sound data generated by the electronic device at the fixed position. For the following detailed description of the difference portions, other portions are not described again, and details are not described as much, please refer to the above embodiment, and the method may include, for example, operations S301 to S306.
In operation S301, first sound data and a predetermined noise angle of an omni-bearing environment when the electronic device is in operation are pre-stored.
In operation S302, ambient sound data generated when the electronic device operates and second sound data generated when the electronic device is fixed to a position where the electronic device operates are obtained, and noise reduction processing is performed on the ambient sound data according to the first sound data to obtain first noise reduction data.
When the environmental sound data of the electronic equipment during working is obtained, second sound data generated by the fixed position of the electronic equipment is also obtained. The second sound data is motor noise data acquired by a directional sound acquisition device (directional microphone) in order to further reduce noise of the first noise reduction data according to noise data acquired at a specific angle.
In operation S303, it is determined whether the frequency of the second sound data is greater than a preset threshold.
When the frequency of the second sound data exceeds the preset threshold, operation S304 is performed. Wherein the preset threshold is adjusted according to the actual voice recognition effect.
When the frequency of the second sound data is not more than the preset threshold, the first noise reduction data does not need to be subjected to noise reduction according to the second sound data. Only operation S305 needs to be performed.
In operation S304, noise reduction processing is performed on the first noise reduction data according to the second sound data, resulting in third noise reduction data.
Specifically, first, a second weighting factor is set for the second sound data, and the second weighting factor may be adjusted according to the actual recognition effect, which is not limited in the invention. And secondly, performing multiplication operation on the second sound data and the second weighting factor to obtain second weighted noise data. And finally, performing subtraction operation on the first noise reduction data and the second weighted noise data to further remove the motor noise data in the first noise data to obtain third noise reduction data.
In operation S305, data corresponding to a predetermined noise angle is removed from the noise reduction data obtained in operation S303 or operation S304, resulting in second noise reduction data.
And when the frequency of the second sound data is not more than the preset threshold value, the first noise data does not need to be subjected to noise reduction processing to obtain third noise data, and then the third noise data is subjected to noise reduction. And directly reading a pre-stored noise angle, namely the azimuth of the motor, suppressing the noise of the azimuth, and removing the noise data which is in accordance with the preset noise angle from the first noise reduction data.
When the frequency of the second sound data exceeds a preset threshold, first, the first noise data needs to be subjected to double-microphone noise reduction according to the obtained second sound data, part of motor noise is removed, third noise reduction data is obtained, then a pre-stored noise angle, namely the direction of the motor, is read, noise in the direction is suppressed, and noise data which are in line with the preset noise angle in the third noise reduction data are removed.
In operation S306, speech recognition is performed on the second noise reduction data.
In this embodiment, not only make an uproar is tentatively fallen to the environmental sound including voice command based on the all-round motor noise data of electronic equipment during operation that acquire, gets rid of a part motor noise, still further falls the noise to environmental sound based on the noise data of the fixed angle (motor position) orientation of electronic equipment that acquire, simultaneously, suppresses the noise based on motor noise angle, further gets rid of motor noise again to further improve speech recognition's rate of accuracy.
In the embodiment of the sound processing method, there is no strict sequence between the operation steps, and in the practical application process, the operation steps can be executed in parallel, and the step writing does not limit the method of the embodiment of the present disclosure to be executed strictly according to the steps.
FIG. 4 is a block diagram illustrating an electronic device in accordance with an example embodiment.
As shown in fig. 4, the electronic device may apply the sound processing method described above. The electronic device may include, for example, a sound collection array 410, a first processing unit 420, a second processing unit 430, a third processing unit 440, a speech recognition unit 450, and a control unit 460.
The sound collection array 410 may be used, for example, to acquire sound data. Each unit in the sound collection array 410 includes a first sound collection unit and a second sound collection unit, where the first sound collection unit is configured to obtain first sound data of the electronic device in all directions during operation and environmental sound data of the electronic device during operation, and the second sound collection unit is configured to obtain second sound data generated by the electronic device at a fixed location.
The sound collection array 410 may be, for example, a microphone array, and the first sound collection unit may use, for example, an omni-directional microphone, and the second sound collection unit may use, for example, a directional microphone. When the microphone picking-up device works, the microphone data of the two paths are processed, the noise data of the directional microphone motor in the omnidirectional microphone picking-up data are eliminated, and finally, one path of effective data is obtained and is processed for the main control chip.
As shown in fig. 5, MIC11 and MIC12 are placed at the same position, MIC11 is an omnidirectional microphone, and MIC12 is a directional microphone, and points to the inside of the machine to pick up noise inside the machine. MIC21, MIC22 put in same position, MIC21 is the omnidirectional microphone, MIC22 is the directional microphone, points to the inside of the machine, picks up the internal noise of machine. And so on.
A Low Pass Filter (LPF) may be added to the sound collection array 410, as shown in fig. 6, to filter out data in the microphone collection environment sound data that has a frequency higher than the human voice frequency.
Moreover, the power circuit part of the electronic device and the power part of the sound collection array 410 realize power isolation, as shown in fig. 7, the circuit isolation method avoids the power noise of the power circuit part of the electronic device from influencing the microphone array circuit, and reduces the noise.
The first processing unit 420 may be configured to perform noise reduction processing on the ambient sound data according to the first sound data, for example, to obtain first noise reduction data.
The second processing unit 430 may be configured to remove data that meets a predetermined noise angle from the first noise reduction data, for example, to obtain second noise reduction data.
The second processing unit 440 may be configured to, for example, perform noise reduction processing on the first noise reduction data according to the second sound data when the second sound data is greater than a threshold value to obtain third noise reduction data, and remove data that meets a predetermined noise angle from the third noise reduction data to obtain second noise reduction data.
The speech recognition unit 450 may be used to perform speech recognition on the second noise reduction data, for example, to obtain a control instruction.
The control unit 460 may be used, for example, to control the actions of the electronic device according to control instructions.
The electronic equipment can improve the accuracy of the received voice command recognition by the electronic equipment by applying the voice processing method, and reduces faults in the working process.
Fig. 8 is a block diagram illustrating a sound processing apparatus according to an example embodiment.
As shown in fig. 8, the sound processing apparatus 800 may include, for example, a pre-storing module 810, an obtaining module 820, a first processing module 830, a second processing module 840, a third processing module 850, and a voice recognition module 860. The processing means may perform the method as described above with reference to the method embodiment section.
Specifically, the pre-storing module 810 can be used to pre-store the first sound data and the predetermined noise angle of the electronic device in all directions during operation.
The obtaining module 820 may be used to obtain, for example, environmental sound data generated when the electronic device is operating and second sound data generated by a fixed location of the electronic device.
The first processing module 830 may be configured to perform noise reduction processing on the ambient sound data according to the first sound data, for example, to obtain first noise reduction data.
The second processing module 840 may, for example, remove data that meets a predetermined noise angle from the first noise reduction data to obtain second noise reduction data.
For example, when the second sound data is greater than a threshold, the third processing module 850 may perform noise reduction processing on the first noise reduction data according to the second sound data to obtain third noise reduction data, and remove data that meets a predetermined noise angle from the third noise reduction data to obtain second noise reduction data.
The speech recognition module 860 may be used, for example, to perform speech recognition on the second noise reduction data, resulting in a control instruction.
This sound processing apparatus 800 not only makes an initial uproar falls to the environmental sound including voice command based on the all-round motor noise data of the electronic equipment during operation that acquires, gets rid of a part motor noise, still further makes an uproar falls to environmental sound based on the noise data of the fixed angle (motor position) orientation of electronic equipment that acquires, and simultaneously, suppresses the noise based on motor noise angle, further gets rid of motor noise again to further improve speech recognition's accuracy.
It should be noted that the embodiments of the electronic device portion and the apparatus portion are similar to the embodiments of the method portion, and for details, please refer to the method embodiment portion, which is not described herein again.
Any of the modules, units, or at least part of the functionality of any of them according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules and units according to the embodiments of the present disclosure may be implemented by being split into a plurality of modules. Any one or more of the modules, units according to the embodiments of the present disclosure may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by any other reasonable means of hardware or firmware by integrating or packaging the circuits, or in any one of three implementations of software, hardware and firmware, or in any suitable combination of any of them. Alternatively, one or more of the modules, units according to embodiments of the present disclosure may be implemented at least partly as computer program modules, which, when executed, may perform the respective functions.
For example, any plurality of the pre-storing module 810, the obtaining module 820, the first processing module 830, the second processing module 840, the third processing module 850, and the voice recognition module 860 may be combined in one module to be implemented, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the pre-storage module 810, the obtaining module 820, the first processing module 830, the second processing module 840, the third processing module 850, and the voice recognition module 860 may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented by any one of three implementations of software, hardware, and firmware, or by a suitable combination of any several of them. Alternatively, at least one of the pre-storing module 810, the obtaining module 820, the first processing module 830, the second processing module 840, the third processing module 850, and the voice recognition module 860 may be at least partially implemented as a computer program module, which may perform a corresponding function when executed.
FIG. 9 is a block diagram illustrating an electronic device in accordance with an example embodiment. The electronic device shown in fig. 9 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 9, the electronic device 900 includes a processor 910, a computer-readable storage medium 920. The electronic device 900 may perform a method according to an embodiment of the disclosure.
In particular, processor 910 may include, for example, a general purpose microprocessor, an instruction set processor and/or related chip set and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), and/or the like. The processor 910 may also include onboard memory for caching purposes. The processor 910 may be a single processing unit or a plurality of processing units for performing the different actions of the method flows according to embodiments of the present disclosure.
Computer-readable storage media 920, for example, may be non-volatile computer-readable storage media, specific examples including, but not limited to: magnetic storage devices, such as magnetic tape or Hard Disk Drives (HDDs); optical storage devices, such as compact disks (CD-ROMs); memory such as Random Access Memory (RAM) or flash memory, etc.
The computer-readable storage medium 920 may include a computer program 921, which computer program 921 may include code/computer-executable instructions that, when executed by the processor 910, cause the processor 910 to perform a method according to an embodiment of the present disclosure, or any variation thereof.
The computer program 921 may be configured with, for example, computer program code comprising computer program modules. For example, in an example embodiment, code in computer program 921 may include one or more program modules, including 921A, modules 921B, … …, for example. It should be noted that the division and number of the modules are not fixed, and those skilled in the art may use suitable program modules or program module combinations according to actual situations, so that the processor 910 may execute the method according to the embodiment of the present disclosure or any variation thereof when the program modules are executed by the processor 910.
At least one of the pre-storing module 810, the obtaining module 820, the first processing module 830, the second processing module 840, the third processing module 850, and the voice recognition module 860 according to embodiments of the present disclosure may be implemented as a computer program module described with reference to fig. 9, which, when executed by the processor 910, may implement the corresponding operations described above.
The present disclosure also provides a computer-readable storage medium, which may be included in the apparatus/device/system described in the above embodiments, or may exist separately without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It will be understood by those skilled in the art that while the present disclosure has been shown and described with reference to certain exemplary embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present disclosure as defined by the appended claims and their equivalents. Accordingly, the scope of the present disclosure should not be limited to the above-described embodiments, but should be defined not only by the appended claims, but also by equivalents thereof.
Claims (13)
1. A sound processing method for processing environmental sound acquired by an electronic device, the method comprising:
pre-storing first sound data and a preset noise angle of the electronic equipment in all directions during working;
acquiring environmental sound data of the electronic equipment during working, and performing noise reduction processing on the environmental sound data according to the first sound data to obtain first noise reduction data;
removing data which accord with the preset noise angle in the first noise reduction data to obtain second noise reduction data;
and performing voice recognition on the second noise reduction data.
2. The method according to claim 1, wherein when acquiring the environmental sound data of the electronic device during operation, further acquiring second sound data generated by the electronic device at a fixed location, wherein in a case that a frequency of the second sound data is greater than a preset threshold, removing data that meets the predetermined noise angle from the first noise reduction data to obtain second noise reduction data comprises:
performing noise reduction processing on the first noise reduction data according to the second sound data to obtain third noise reduction data;
and removing the data which accord with the preset noise angle in the third noise reduction data to obtain the second noise reduction data.
3. The method of claim 1, wherein the denoising the ambient sound data from the first sound data comprises:
setting a first weighting factor for the first sound data;
calculating the first sound data and the first weight factor to obtain first weighted noise data;
and calculating the environmental sound data and the first weighted noise data to obtain the first noise reduction data.
4. The method of claim 2, wherein the denoising the first denoising data according to the second acoustic data to obtain third denoising data, comprises:
setting a second weighting factor for the second sound data;
calculating the second sound data and the second weight factor to obtain second weighted noise data;
and calculating the first noise reduction data and the second weighted noise data to obtain the third noise reduction data.
5. The method of claim 1, wherein the obtaining environmental sound data of the electronic device during operation comprises:
and filtering data with the frequency higher than the preset frequency in the environmental sound data.
6. The method according to claim 3 or 4, wherein the first sound data is multiplied by the first weighting factor, and the second sound data is multiplied by the second weighting factor;
subtracting the ambient sound data from the first weighted noise data, and subtracting the ambient sound data from the second weighted noise data.
7. The method of claim 5, wherein the preset frequency is set to a human acoustic frequency.
8. An electronic device, comprising:
each unit of the sound collection array comprises a first sound collection unit and a second sound collection unit, wherein the first sound collection unit is used for acquiring first sound data of the electronic equipment in all directions during working and environment sound data of the electronic equipment during working, and the second sound collection unit is used for acquiring second sound data generated by the electronic equipment at a fixed position;
the first processing unit is used for carrying out noise reduction processing on the environmental sound data according to the first sound data to obtain first noise reduction data;
the second processing unit is used for removing the data which accord with the preset noise angle in the first noise reduction data to obtain second noise reduction data;
the voice recognition unit is used for carrying out voice recognition on the second noise reduction data to obtain a control instruction;
and the control unit is used for controlling the action of the electronic equipment according to the control instruction.
9. The electronic device of claim 8, further comprising:
and the third processing unit is used for carrying out noise reduction processing on the first noise reduction data according to the second sound data under the condition that the second sound data is larger than a preset threshold value to obtain third noise reduction data, and then removing data which accord with the preset noise angle in the third noise reduction data to obtain the second noise reduction data.
10. The electronic device of claim 8, further comprising:
and the low-pass filter circuit is used for filtering data with the frequency higher than a preset frequency in the environmental sound data.
11. The electronic device of claim 8, wherein the sound collection array is equipped with an independent power source.
12. A sound processing apparatus for processing an environmental sound acquired by an electronic device, the apparatus comprising:
the pre-storing module is used for pre-storing the omnidirectional first sound data and the preset noise angle when the electronic equipment works;
the acquisition module is used for acquiring environmental sound data when the electronic equipment works;
the first processing module is used for carrying out noise reduction processing on the environmental sound data according to the first sound data to obtain first noise reduction data;
the second processing module is used for removing data which accord with the preset noise angle in the first noise reduction data to obtain second noise reduction data;
and the voice recognition module is used for carrying out voice recognition on the second noise reduction data.
13. A computer-readable storage medium storing computer-executable instructions for implementing the method of any one of claims 1 to 7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910922365.2A CN112562713A (en) | 2019-09-26 | 2019-09-26 | Sound processing method, sound processing device, electronic device, and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910922365.2A CN112562713A (en) | 2019-09-26 | 2019-09-26 | Sound processing method, sound processing device, electronic device, and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112562713A true CN112562713A (en) | 2021-03-26 |
Family
ID=75030309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910922365.2A Pending CN112562713A (en) | 2019-09-26 | 2019-09-26 | Sound processing method, sound processing device, electronic device, and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112562713A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060032877A (en) * | 2004-10-13 | 2006-04-18 | 엘지전자 주식회사 | Voice recognition system and method in using for robot cleaner |
| CN104200817A (en) * | 2014-07-31 | 2014-12-10 | 广东美的制冷设备有限公司 | Speech control method and system |
| CN108231075A (en) * | 2017-12-29 | 2018-06-29 | 北京视觉世界科技有限公司 | Control method, device, equipment and the storage medium of cleaning equipment |
| CN108682428A (en) * | 2018-08-27 | 2018-10-19 | 珠海市微半导体有限公司 | The processing method of robot voice control system and robot to voice signal |
| CN109545210A (en) * | 2018-12-03 | 2019-03-29 | 北京云知声信息技术有限公司 | A kind of devices and methods therefor promoting speech recognition robustness |
| CN109545238A (en) * | 2018-12-11 | 2019-03-29 | 珠海市微半导体有限公司 | A kind of speech de-noising device and robot based on clean robot |
-
2019
- 2019-09-26 CN CN201910922365.2A patent/CN112562713A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060032877A (en) * | 2004-10-13 | 2006-04-18 | 엘지전자 주식회사 | Voice recognition system and method in using for robot cleaner |
| CN104200817A (en) * | 2014-07-31 | 2014-12-10 | 广东美的制冷设备有限公司 | Speech control method and system |
| CN108231075A (en) * | 2017-12-29 | 2018-06-29 | 北京视觉世界科技有限公司 | Control method, device, equipment and the storage medium of cleaning equipment |
| CN108682428A (en) * | 2018-08-27 | 2018-10-19 | 珠海市微半导体有限公司 | The processing method of robot voice control system and robot to voice signal |
| CN109545210A (en) * | 2018-12-03 | 2019-03-29 | 北京云知声信息技术有限公司 | A kind of devices and methods therefor promoting speech recognition robustness |
| CN109545238A (en) * | 2018-12-11 | 2019-03-29 | 珠海市微半导体有限公司 | A kind of speech de-noising device and robot based on clean robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107577449B (en) | Wake-up voice pickup method, device, equipment and storage medium | |
| US11074924B2 (en) | Speech recognition method, device, apparatus and computer-readable storage medium | |
| CN107591151B (en) | Far-field voice awakening method and device and terminal equipment | |
| CN110010126B (en) | Speech recognition method, apparatus, device and storage medium | |
| CN107910013B (en) | Voice signal output processing method and device | |
| CN108681440A (en) | A kind of smart machine method for controlling volume and system | |
| US10679617B2 (en) | Voice enhancement in audio signals through modified generalized eigenvalue beamformer | |
| CN109273020B (en) | Audio signal processing method, apparatus, device and storage medium | |
| CN113507662B (en) | Noise reduction processing method, apparatus, device, storage medium, and program | |
| KR20210040006A (en) | Noise reduction method and apparatus for on-board environment, electronic device, storage medium, and program | |
| CN109087660A (en) | Method, apparatus, equipment and computer readable storage medium for echo cancellor | |
| KR20170129697A (en) | Microphone array speech enhancement technique | |
| EP3671271A2 (en) | Near ultrasound based proximity sensing for mobile devices | |
| JP4866958B2 (en) | Noise reduction in electronic devices with farfield microphones on the console | |
| CN113053368A (en) | Speech enhancement method, electronic device, and storage medium | |
| CN112492207A (en) | Method and device for controlling rotation of camera based on sound source positioning | |
| CN112562713A (en) | Sound processing method, sound processing device, electronic device, and medium | |
| CN111103807A (en) | Control method and device for household terminal equipment | |
| CN114302286A (en) | Method, device and equipment for reducing noise of call voice and storage medium | |
| US20200327887A1 (en) | Dnn based processor for speech recognition and detection | |
| CN110265048B (en) | Echo cancellation method, device, equipment and storage medium | |
| CN112562712A (en) | Recording data processing method and system, electronic equipment and storage medium | |
| CN111813365A (en) | Method, device and equipment for preventing interruption of multiple rounds of conversations | |
| CN112309362A (en) | Active acoustic noise reduction method and device of MR system and computer equipment | |
| CN115223548B (en) | Voice interaction method, voice interaction device and storage 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 |