CN112053701A - Sound pickup control method, sound pickup control apparatus, sound pickup control system, sound pickup device, and sound pickup medium - Google Patents
Sound pickup control method, sound pickup control apparatus, sound pickup control system, sound pickup device, and sound pickup medium Download PDFInfo
- Publication number
- CN112053701A CN112053701A CN202010954651.XA CN202010954651A CN112053701A CN 112053701 A CN112053701 A CN 112053701A CN 202010954651 A CN202010954651 A CN 202010954651A CN 112053701 A CN112053701 A CN 112053701A
- Authority
- CN
- China
- Prior art keywords
- noise
- signal
- sound pressure
- microphone
- noise reduction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 69
- 230000009467 reduction Effects 0.000 claims abstract description 100
- 230000007613 environmental effect Effects 0.000 claims abstract description 57
- 230000035945 sensitivity Effects 0.000 claims abstract description 49
- 238000012544 monitoring process Methods 0.000 claims abstract description 11
- 230000005236 sound signal Effects 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 description 30
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000010408 sweeping 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
-
- 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
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 application discloses a pickup control method, apparatus, system, device and medium. The method comprises the following steps: monitoring an ambient noise signal around the microphone; adjusting a sensitivity of the microphone based on a noise sound pressure of the ambient noise signal; receiving a voice signal collected by a microphone; determining a noise reduction model corresponding to noise sound pressure; the speech content of the speech signal is determined using the noise reduction model. The problem that the pickup capacity and the pickup quality of the microphone are easily affected by environmental noise is solved.
Description
Technical Field
The present application relates generally to the field of speech recognition technology, and more particularly, to a method, apparatus, device, and medium for controlling sound pickup.
Background
With the development of artificial intelligence technology, intelligent voice technology has been widely applied to various scientific and technological products, such as intelligent voice furniture, intelligent robots, intelligent playing devices, and the like.
The smart voice device may generally process the acquired voice signal to recognize the voice content and control the smart voice device to perform operations related to the voice content.
Under the general condition, intelligent speech equipment can work in different environment, and when intelligent speech equipment worked in quiet environment, if the user awakens this speech equipment in the sound of suppressing, probably lead to the user can't awaken this speech equipment up, or speech equipment discerns wrong pronunciation content, and intelligent speech equipment pickup capacity and quality are influenced by the environment greatly, influence user's use experience.
Disclosure of Invention
In view of the above-described drawbacks and deficiencies of the prior art, it would be desirable to provide a sound pickup control method, apparatus, system, device, and medium that can reduce the impact of environmental factors on sound pickup capability and quality.
In a first aspect, the present application provides a pickup control method, including:
monitoring an ambient noise signal around the microphone;
adjusting a sensitivity of the microphone based on a noise sound pressure of the ambient noise signal;
receiving a voice signal collected by a microphone;
determining a noise reduction model corresponding to noise sound pressure;
the speech content of the speech signal is determined using the noise reduction model.
In a second aspect, the present application provides a sound pickup control apparatus including:
a monitoring module configured to monitor an ambient noise signal around the microphone;
an adjustment module configured to adjust a sensitivity of the microphone based on a noise sound pressure of the ambient noise signal;
the receiving module is also configured to receive the voice signal collected by the microphone;
a determination module configured to determine a noise reduction model corresponding to a noise sound pressure;
a determination module further configured to determine a speech content of the speech signal using the noise reduction model.
In a third aspect, the present application provides a sound pickup control system, including: at least one microphone and a main control device, the microphone is connected with the main control device,
the microphone is used for acquiring environmental noise around the microphone to generate an environmental noise signal and sending the environmental noise signal to the main control equipment;
and the main control equipment is used for receiving the environmental noise signal, acquiring the content of the voice signal according to the sound pickup control method of the first aspect, and executing the operation corresponding to the voice content.
In a fourth aspect, the present application provides a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor being adapted to perform the method of the first aspect when executing the program;
in a fifth aspect, the present application provides a computer readable storage medium having stored thereon a computer program for implementing the method of the first aspect.
The technical scheme provided by the embodiment of the application can have the following beneficial effects:
the pickup control method, the pickup control device, the pickup control system, the pickup control equipment and the pickup control medium can monitor the ambient noise signals around the microphone; adjusting a sensitivity of the microphone based on a noise sound pressure of the ambient noise signal; receiving a voice signal collected by a microphone; determining a noise reduction model corresponding to noise sound pressure; the speech content of the speech signal is determined using the noise reduction model. The sensitivity of the microphone can be adjusted based on the environmental noise, the influence of the environmental noise on the sound pickup capacity of the microphone is reduced, and the environmental noise in the voice signal corresponding to the noise reduction model corresponding to the current noise environment is selected in a targeted mode to be processed according to different degrees of the environmental noise, so that the accuracy of finally recognized voice content is improved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
fig. 1 is a schematic structural diagram of a pickup control system according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a pickup control method according to an embodiment of the present disclosure;
fig. 3 is a schematic flowchart of another pickup control method according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a pickup control apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of another pickup control apparatus according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a sound pickup control apparatus according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 is a schematic structural diagram of a sound pickup control system according to an embodiment of the present application, and as shown in fig. 1, the sound pickup control system includes: at least one microphone 110 and a master device 120.
After the system is in the power-on state, the microphone 110 may collect environmental noise around the microphone in real time to generate an environmental noise signal, and send the environmental noise signal to the main control device 120, where the environmental noise signal may be a noise signal generated by a household appliance device in an environmental space where the microphone 110 is located, a noise signal emitted when an automobile passes through, and/or a construction noise signal, but is not limited thereto.
The main control device 120 may receive an audio signal sent by a microphone, determine a noise sound pressure of the ambient noise signal, adjust a sensitivity of the microphone based on the noise sound pressure of the ambient noise signal, and receive a voice signal collected by the microphone; determining a noise reduction model corresponding to noise sound pressure; and determining the voice content of the voice signal by using the noise reduction model, and executing the operation corresponding to the voice content.
The microphone 110 and the main control device 120 may be connected through a wired network or a wireless network, the microphone 110 may be a moving coil microphone, a track microphone, or a condenser microphone, and the main control device 120 is a terminal device or a server with data storage and processing functions.
It is understood that the pickup control system may also be integrated into a pickup control apparatus including: the microphone is used for collecting ambient noise around the microphone to generate an ambient noise signal, and the ambient noise signal is sent to the main control module.
The main control module is used for receiving an environment noise signal and adjusting the sensitivity of the microphone based on the noise sound pressure of the environment noise signal; and can receive the voice signal that the microphone obtains; determining a noise reduction model corresponding to noise sound pressure; and determining the voice content of the voice signal by using the noise reduction model, and controlling the pickup control equipment to execute the operation corresponding to the voice content. For example, the pickup control device may be a sweeping robot or a smart playing device.
A pickup control method in this embodiment of the present application, which may be applied to the above-mentioned main control device or main control module, where in this embodiment of the present application, taking the application of the method to the main control device as an example, the method is described, and a process of applying the method to the main control module may refer to this process, which is not described herein again in this embodiment of the present application, as shown in fig. 2, when the method is applied to the main control device, the method includes:
In this step, after the pickup control system is powered on, the microphone may collect environmental noise around the microphone in real time to generate an environmental noise signal, and the environmental noise signal is sent to the main control device, and the main control device may receive the environmental noise signal sent by the microphone; alternatively, the master device may receive an ambient noise signal generated by ambient noise around the audio signal acquisition device acquired by another audio signal acquisition device connected to the master device.
In the embodiment of the present application, the microphones usually operate in different noise environments, the sensitivity of the microphone is closely related to the operating environment of the microphone, the microphone with lower sensitivity can pick up a sound source with quieter or closer distance, the microphone with higher sensitivity is more suitable for picking up a sound source with louder or farther distance of environmental noise, and the sensitivity of the microphone refers to the ratio of the output voltage of the microphone to the input sound pressure under the excitation of unit sound pressure, and the unit of the output voltage is mV/Pa, and can also be a decibel value.
It can be understood that, regarding the working environment of the microphone, even a noisy environment or a quiet environment, the noisy or quiet degree thereof is different, and therefore, in order to ensure that the microphone collects a voice signal in an optimal sensitivity value under different environmental conditions, the noise sound pressure of the environmental noise is generally divided into a plurality of noise sound pressure intervals, a corresponding noise sound pressure level is assigned to each noise sound pressure interval, the sensitivity of the microphone corresponding to each noise sound pressure level is determined based on big data analysis, and the correspondence relationship between the noise sound pressure level and the sensitivity of the microphone is established and stored. The correspondence between the sensitivities of the microphones corresponding to the noise sound pressure levels represents: when the microphone works in the noise environment with the noise sound pressure level, the sensitivity of high-quality voice signals can be acquired.
It should be noted that, in the embodiment of the present application, the division of the noise sound pressure level of the environmental noise may be determined based on actual needs, and the embodiment of the present application does not limit this. However, it can be understood that the more the noise sound pressure levels of the environmental noise are divided, the more the correspondence relationship between the determined sensitivities of the microphones corresponding to the noise sound pressure levels is, the higher the matching degree between the microphone after the sensitivity adjustment and the current environmental condition is in the sensitivity adjustment process of the microphone, and the higher the quality of the voice signal can be acquired.
In this step, the process of the main control device adjusting the sensitivity of the microphone based on the noise sound pressure of the ambient noise signal may include: determining the noise sound pressure level of the environmental noise signal according to the noise sound pressure; determining a preset sensitivity corresponding to the noise sound pressure level of the environmental noise signal according to the noise sound pressure level of the environmental noise signal and the corresponding relation between the noise sound pressure level and the sensitivity of the microphone; and adjusting the sensitivity of the microphone to a preset sensitivity.
And step 203, receiving the voice signal collected by the microphone.
In this step, the microphone with the adjusted sensitivity may collect a target voice to generate a voice signal, and send the voice signal to the main control device, and the main control device may receive the voice signal collected by the microphone.
Optionally, in this embodiment of the application, the voice signal received by the main control device is an audio signal including an ambient noise signal and a target voice signal, and after the main control device receives the voice signal, it may determine a noise sound pressure of the ambient noise signal included in the voice signal, and compare the noise sound pressure with the noise sound pressure of the ambient noise in step 202, if the two are different, the method in step 202 is used to continuously adjust the sensitivity of the microphone, and if the two are the same, the microphone is controlled to maintain the current sensitivity, and the voice signal is continuously acquired. The method can further ensure that the sensitivity of the microphone can be adjusted in real time according to the change of the environmental noise in the acquisition process of the voice signals, and the quality of the voice signals acquired by the microphone is ensured.
And step 204, determining a noise reduction model corresponding to the noise sound pressure.
In the embodiment of the application, when the microphone works in noise environments with different degrees, the voice signals acquired by using different sensitivities have different audio characteristics, in order to improve the accuracy of processing the voice signals, in the processing process of the voice signals, different noise reduction models can be used for carrying out noise reduction processing on the voice signals acquired by the microphone according to different degrees of current environmental noise, and for the voice signals acquired in the high-noise environment, the noise reduction model has higher noise reduction amplitude in the process of carrying out noise reduction processing on the voice signals, so that the environmental noise can be filtered as much as possible to acquire more target sounds; for the voice signals collected in the low-noise environment, the noise reduction model has lower noise reduction amplitude in the process of carrying out noise reduction processing on the voice signals, and can prevent target sound signals from being filtered so as to reserve more target sounds.
It is understood that, in the embodiment of the present application, in order to implement high-precision processing on speech signals acquired in different noise environments, the noise reduction model for performing noise reduction processing on the acquired speech signals may include a first noise reduction model for performing noise reduction processing on speech signals acquired in a high-noise environment and a second noise reduction model for performing noise reduction processing on speech signals acquired in a low-noise environment, where a noise sound pressure of the high-noise environment is greater than a sound pressure threshold, and a noise sound pressure of the high-noise environment is greater than the sound pressure threshold.
In this step, the process of determining the noise reduction model corresponding to the noise sound pressure may be: judging whether the noise sound pressure of the environmental noise signal is greater than a sound pressure threshold value or not; when the noise sound pressure is greater than the sound pressure threshold value, determining that the current environment is a high-noise environment, and determining that a noise reduction model corresponding to the noise sound pressure is a first noise reduction model; when the noise sound pressure is smaller than the sound pressure threshold value, determining that the current environment is a low-noise environment, and determining that the noise reduction model corresponding to the noise sound pressure is a second noise reduction model; the sound pressure threshold is the boundary sound pressure of a predefined high-noise environment and a predefined low-noise environment; the sound pressure threshold may be determined based on actual needs, which is not limited in the embodiments of the present application.
It should be noted that, in the embodiment of the present application, the sequence of step 203 and step 204 is not strictly limited, and the sequence of step 203 and step 204 does not affect the implementation of the sound pickup control method.
In this step, because different noise reduction models can be used for noise reduction processing on the speech signal collected in the high-noise environment and the speech signal collected in the low-noise environment, the process of determining the speech content of the speech signal by using the noise reduction models can have the following two optional implementation manners:
in an alternative implementation: when the determined noise model is the first noise reduction model, the process of determining the speech content of the speech signal using the noise reduction model may be: the main control device can input the voice signal into a first noise reduction model, the first noise reduction model can pre-process the voice signal to obtain a pre-processed voice signal, and perform first noise reduction processing on the pre-processed voice signal to filter a first noise signal to obtain a target voice signal; the master device may then input the target sound signal into a speech recognition model, which may determine speech content corresponding to the speech signal. Wherein the first noise reduction model may be a noise reduction model established based on a beamforming or blind source separation algorithm, the first noise signal may include the first ambient noise, or the first noise signal may include the first ambient noise and a non-target audio signal, for example, the non-target audio signal may be an audio signal generated by a microphone acquiring music played by a playing device, and/or an audio signal generated by a microphone acquiring whisper when someone else speaks.
In another alternative implementation, when the determined noise model is the second noise reduction model, the process of determining the speech content of the speech signal by using the noise reduction model may be: the main control device may input the voice signal into a second noise reduction model, where the second noise reduction model may pre-process the voice signal to obtain a pre-processed voice signal; carrying out second noise reduction processing on the preprocessed voice signal to filter a second noise signal and obtain a target voice signal; the master device may then input the target sound signal into a speech recognition model, which may determine speech content corresponding to the speech signal. Wherein the second noise reduction model may be a noise reduction model established based on a neural network, the second noise signal includes a second ambient noise, and a non-target audio signal, and a noise sound pressure of the first ambient noise signal is greater than a noise sound pressure of the second ambient noise signal.
It should be noted that, in the embodiment of the present application, the first denoising process is a process of filtering a first ambient noise signal in a speech signal, or the first denoising process is a process of filtering a first ambient noise signal and a non-target sound signal in a speech signal, the second denoising process is a process of filtering a second ambient noise signal in a speech signal, or the second denoising process is a process of filtering a second ambient noise signal and a non-target sound signal in a speech signal, since a noise sound pressure of the first ambient noise signal is greater than a noise sound pressure of the second ambient noise signal, in the first denoising process, a first denoising strength of the first ambient noise signal by the first denoising model is greater than a second denoising strength of the second ambient noise signal by the second denoising model, the magnitude of the first noise reduction strength may be determined by the first noise reduction model based on the strength of the first ambient noise signal, and the magnitude of the second noise reduction strength may be determined by the second noise reduction model based on the strength of the second ambient noise signal, which is not limited in the embodiment of the present application.
The process of determining the voice content corresponding to the voice signal by the voice recognition model is as follows: and converting the target sound signal into a character signal through a voice recognition model established based on the acoustic model, the language model and the neural network, and further performing semantic analysis on the character signal through a semantic recognition algorithm to determine a recognition result and acquire voice content corresponding to the voice signal.
In summary, the pickup control method provided in the embodiment of the present application may monitor an ambient noise signal around a microphone; adjusting a sensitivity of the microphone based on a noise sound pressure of the ambient noise signal; receiving a voice signal collected by a microphone; determining a noise reduction model corresponding to noise sound pressure; the speech content of the speech signal is determined using the noise reduction model. The sensitivity of the microphone can be adjusted based on the environmental noise, the influence of the environmental noise on the sound pickup capacity of the microphone is reduced, and the environmental noise in the voice signal corresponding to the noise reduction model corresponding to the current noise environment is selected in a targeted mode to be processed according to different degrees of the environmental noise, so that the accuracy of finally recognized voice content is improved.
An embodiment of the present application provides a pickup control method, which may be applied to the above-mentioned main control device or main control module, and as shown in fig. 3, the method includes:
In this embodiment, the process of step 302 may refer to step 202, which is not described in this embodiment.
And step 303, receiving the voice signal collected by the microphone.
And step 304, determining a noise reduction model corresponding to the noise sound pressure.
In this embodiment, the process of step 304 may refer to step 204, which is not described in detail in this embodiment.
In this embodiment, the process of step 305 may refer to step 205, which is not described in detail in this embodiment.
And step 306, executing the operation corresponding to the voice content.
In this step, the main control device or the main control module may determine a control instruction in the voice content according to the voice content, and execute a control operation corresponding to the control instruction according to the control instruction. For example, if the control instruction in the obtained voice content is analyzed as "broadcast weather", the current weather condition may be obtained, and the sound box is controlled to play the weather condition, and if the control instruction in the obtained voice content is analyzed as "turn up volume", the volume of the sound box may be controlled to be adjusted to play the content being played currently.
In summary, the pickup control method provided in the embodiment of the present application may monitor an ambient noise signal around a microphone; adjusting a sensitivity of the microphone based on a noise sound pressure of the ambient noise signal; receiving a voice signal collected by a microphone; determining a noise reduction model corresponding to noise sound pressure; and determining the voice content of the voice signal by using the noise reduction model, and executing the operation corresponding to the voice content. The sensitivity of the microphone can be adjusted based on the environmental noise, the influence of the environmental noise on the sound pickup capacity of the microphone is reduced, and the environmental noise in the voice signal corresponding to the noise reduction model corresponding to the current noise environment is selected in a targeted mode to be processed according to different degrees of the environmental noise, so that the accuracy of finally recognized voice content is improved.
An embodiment of the present application provides a sound pickup control apparatus, as shown in fig. 4, the apparatus 40 includes:
a monitoring module 401 configured to monitor an ambient noise signal around the microphone;
an adjustment module 402 configured to adjust a sensitivity of the microphone based on a noise sound pressure of the ambient noise signal;
a receiving module 403 configured to receive a voice signal collected by a microphone;
a determining module 404 configured to determine a noise reduction model corresponding to the noise sound pressure;
the determination module 404 is further configured to determine a speech content of the speech signal using the noise reduction model.
Optionally, the adjusting module 402 is configured to include:
determining the noise sound pressure level of the environmental noise signal according to the noise sound pressure;
determining a preset sensitivity corresponding to the noise sound pressure level of the environmental noise signal according to the noise sound pressure level of the environmental noise signal and the corresponding relation between the noise sound pressure level and the sensitivity of the microphone;
and adjusting the sensitivity of the microphone to a preset sensitivity.
Optionally, the determining module 404 is configured to:
judging whether the noise sound pressure is greater than a sound pressure threshold value;
when the noise sound pressure is larger than the sound pressure threshold value, determining a noise reduction model corresponding to the noise sound pressure as a first noise reduction model;
and when the noise sound pressure is smaller than the sound pressure threshold value, determining that the noise reduction model corresponding to the noise sound pressure is a second noise reduction model.
Optionally, when the noise model is the first noise reduction model, the determining module 404 is configured to:
inputting a speech signal into a first noise reduction model;
performing first noise reduction processing on the voice signal by using a first noise reduction model to filter a first noise signal, and acquiring a target voice signal, wherein the first noise signal comprises a first environmental noise signal;
inputting the target sound signal into a speech recognition model to determine the speech content corresponding to the speech signal.
Optionally, when the noise model is the second noise reduction model, the determining module 404 is configured to:
inputting the voice signal into a second noise reduction model;
performing second noise reduction processing on the voice signal by using a second noise reduction model to filter a second noise signal, so as to obtain a target sound signal, wherein the second noise signal comprises a second environment noise signal, and the noise sound pressure of the first environment noise signal is greater than that of the second environment noise signal;
inputting the target sound signal into a speech recognition model to determine the speech content corresponding to the speech signal.
Optionally, as shown in fig. 5, the apparatus 40 further includes:
an execution module 405 configured to execute an operation corresponding to the voice content.
In summary, the sound pickup control apparatus provided in the embodiment of the present application can monitor an ambient noise signal around a microphone; adjusting a sensitivity of the microphone based on a noise sound pressure of the ambient noise signal; receiving a voice signal collected by a microphone; determining a noise reduction model corresponding to noise sound pressure; the speech content of the speech signal is determined using the noise reduction model. The sensitivity of the microphone can be adjusted based on the environmental noise, the influence of the environmental noise on the sound pickup capacity of the microphone is reduced, and the environmental noise in the voice signal corresponding to the noise reduction model corresponding to the current noise environment is selected in a targeted mode to be processed according to different degrees of the environmental noise, so that the accuracy of finally recognized voice content is improved.
Fig. 6 is a diagram illustrating a computer system according to an exemplary embodiment, which includes a Central Processing Unit (CPU)501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for system operation are also stored. The CPU501, ROM502, and RAM503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output section including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The drives are also connected to the I/O interface 505 as needed. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.
In particular, the processes described above in fig. 2-3 may be implemented as computer software programs, according to embodiments of the present application. For example, various embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section, and/or installed from a removable medium. The above-described functions defined in the system of the present application are executed when the computer program is executed by the Central Processing Unit (CPU) 501.
It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods, apparatus, and computer program products according to various embodiments of the present application. 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.
The units described in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves. The described units or modules may also be provided in a processor, and may be described as: a processor includes a monitoring module, an adjustment module, a receiving module, and a determination module. The names of these units or modules do not in some cases constitute a limitation of the units or modules themselves, for example, the monitoring module may also be described as "a monitoring module for monitoring an ambient noise signal around a microphone".
As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs that, when executed by one of the electronic apparatuses, cause the electronic apparatus to implement the sound pickup control method as in the above-mentioned embodiments.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by a person skilled in the art that the scope of the invention as referred to in the present application is not limited to the embodiments with a specific combination of the above-mentioned features, but also covers other embodiments with any combination of the above-mentioned features or their equivalents without departing from the inventive concept. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (10)
1. A sound pickup control method, characterized by comprising:
monitoring an ambient noise signal around the microphone;
adjusting a sensitivity of the microphone based on a noise sound pressure of the ambient noise signal;
receiving a voice signal collected by the microphone;
determining a noise reduction model corresponding to the noise sound pressure;
and determining the voice content of the voice signal by using the noise reduction model.
2. The method of claim 1, wherein the adjusting the sensitivity of the microphone based on the noise sound pressure of the ambient noise signal comprises:
determining the noise sound pressure level of the environment noise signal according to the noise sound pressure;
determining preset sensitivity corresponding to the noise sound pressure level of the environmental noise signal according to the noise sound pressure level of the environmental noise signal and the corresponding relation between the noise sound pressure level and the sensitivity of a microphone;
and adjusting the sensitivity of the microphone to the preset sensitivity.
3. The method of claim 1, wherein determining a noise reduction model corresponding to the noise acoustic pressure comprises:
judging whether the noise sound pressure is greater than a sound pressure threshold value;
when the noise sound pressure is larger than the sound pressure threshold value, determining that a noise reduction model corresponding to the noise sound pressure is a first noise reduction model;
and when the noise sound pressure is smaller than the sound pressure threshold value, determining that the noise reduction model corresponding to the noise sound pressure is a second noise reduction model.
4. The method of claim 3, wherein when the noise model is the first noise reduction model, the determining the speech content of the speech signal using the noise reduction model comprises:
inputting the speech signal into the first noise reduction model;
performing first noise reduction processing on the voice signal by using the first noise reduction model to filter a first noise signal, and acquiring a target sound signal, wherein the first noise signal comprises a first environmental noise signal;
inputting the target sound signal into a voice recognition model to determine the voice content corresponding to the voice signal.
5. The method of claim 3, wherein when the noise model is the second noise reduction model, the inputting the speech signal into the noise reduction model to obtain a target sound signal comprises:
inputting the speech signal into the second noise reduction model;
performing second noise reduction processing on the voice signal by using the second noise reduction model to filter a second noise signal, so as to obtain a target sound signal, wherein the second noise signal comprises a second environmental noise signal, and the noise sound pressure of the first environmental noise signal is greater than that of the second environmental noise signal;
inputting the target sound signal into a voice recognition model to determine the voice content corresponding to the voice signal.
6. The method of any of claims 1-5, wherein after determining the speech content of the speech signal using the noise reduction model, the method further comprises:
and executing the operation corresponding to the voice content.
7. A sound pickup control apparatus, comprising:
a monitoring module configured to monitor an ambient noise signal around the microphone;
an adjustment module configured to adjust a sensitivity of the microphone based on a noise sound pressure of the ambient noise signal;
a receiving module, further configured to receive the voice signal collected by the microphone;
a determination module configured to determine a noise reduction model corresponding to the noise sound pressure;
the determination module is further configured to determine a speech content of the speech signal using the noise reduction model.
8. A pickup control system, comprising: at least one microphone and a master control device, the microphone being connected to the master control device,
the microphone is used for acquiring environmental noise around the microphone to generate an environmental noise signal and sending the environmental noise signal to the main control equipment;
the main control device is configured to receive the ambient noise signal, acquire content of a voice signal according to the sound pickup control method according to any one of claims 1 to 6, and perform an operation corresponding to the content of the voice signal.
9. A computer device, characterized in that the computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, the processor being adapted to implement the method according to any of claims 1-6 when executing the program.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon for implementing the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010954651.XA CN112053701A (en) | 2020-09-11 | 2020-09-11 | Sound pickup control method, sound pickup control apparatus, sound pickup control system, sound pickup device, and sound pickup medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010954651.XA CN112053701A (en) | 2020-09-11 | 2020-09-11 | Sound pickup control method, sound pickup control apparatus, sound pickup control system, sound pickup device, and sound pickup medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112053701A true CN112053701A (en) | 2020-12-08 |
Family
ID=73610063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010954651.XA Pending CN112053701A (en) | 2020-09-11 | 2020-09-11 | Sound pickup control method, sound pickup control apparatus, sound pickup control system, sound pickup device, and sound pickup medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112053701A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112735457A (en) * | 2020-12-11 | 2021-04-30 | 中国汽车技术研究中心有限公司 | Voice denoising method and system |
| CN112786042A (en) * | 2020-12-28 | 2021-05-11 | 北京百度网讯科技有限公司 | Method, device and equipment for adjusting vehicle-mounted voice equipment and storage medium |
| CN113163282A (en) * | 2021-03-31 | 2021-07-23 | 深圳鱼亮科技有限公司 | Noise reduction pickup system and method based on USB |
| WO2021258724A1 (en) * | 2020-06-22 | 2021-12-30 | 中兴通讯股份有限公司 | Terminal, sound production method, storage medium, and electronic device |
| CN114007157A (en) * | 2021-10-28 | 2022-02-01 | 中北大学 | An intelligent noise-cancelling communication headset |
| CN114153314A (en) * | 2021-11-29 | 2022-03-08 | 重庆长安汽车股份有限公司 | In-vehicle noise dynamic display interaction method and system for enhancing user experience |
| CN114255779A (en) * | 2021-12-17 | 2022-03-29 | 思必驰科技股份有限公司 | Audio noise reduction method, electronic device and storage medium for VR device |
| CN115831110A (en) * | 2022-11-02 | 2023-03-21 | 广东美的厨房电器制造有限公司 | Noise reduction method, electronic device and storage device |
| CN119763564A (en) * | 2024-11-22 | 2025-04-04 | 成都理工大学 | Embedded speech recognition control module and its device interaction system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100274564A1 (en) * | 2009-04-28 | 2010-10-28 | Pericles Nicholas Bakalos | Coordinated anr reference sound compression |
| CN105979415A (en) * | 2016-05-30 | 2016-09-28 | 歌尔股份有限公司 | Noise reduction method capable of realizing self-adaptive adjustment of noise reduction gain, device thereof, and noise reduction earphone |
| CN110460921A (en) * | 2019-07-15 | 2019-11-15 | 中国第一汽车股份有限公司 | A kind of pick-up control method, device, vehicle and storage medium |
| CN111295707A (en) * | 2017-10-30 | 2020-06-16 | 伯斯有限公司 | Compression hear-through in personal acoustic devices |
-
2020
- 2020-09-11 CN CN202010954651.XA patent/CN112053701A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100274564A1 (en) * | 2009-04-28 | 2010-10-28 | Pericles Nicholas Bakalos | Coordinated anr reference sound compression |
| CN105979415A (en) * | 2016-05-30 | 2016-09-28 | 歌尔股份有限公司 | Noise reduction method capable of realizing self-adaptive adjustment of noise reduction gain, device thereof, and noise reduction earphone |
| CN111295707A (en) * | 2017-10-30 | 2020-06-16 | 伯斯有限公司 | Compression hear-through in personal acoustic devices |
| CN110460921A (en) * | 2019-07-15 | 2019-11-15 | 中国第一汽车股份有限公司 | A kind of pick-up control method, device, vehicle and storage medium |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021258724A1 (en) * | 2020-06-22 | 2021-12-30 | 中兴通讯股份有限公司 | Terminal, sound production method, storage medium, and electronic device |
| CN112735457A (en) * | 2020-12-11 | 2021-04-30 | 中国汽车技术研究中心有限公司 | Voice denoising method and system |
| CN112735457B (en) * | 2020-12-11 | 2022-05-17 | 中国汽车技术研究中心有限公司 | Voice denoising method and system |
| CN112786042A (en) * | 2020-12-28 | 2021-05-11 | 北京百度网讯科技有限公司 | Method, device and equipment for adjusting vehicle-mounted voice equipment and storage medium |
| CN112786042B (en) * | 2020-12-28 | 2024-05-31 | 阿波罗智联(北京)科技有限公司 | Adjustment method, device, equipment and storage medium of vehicle-mounted voice equipment |
| CN113163282A (en) * | 2021-03-31 | 2021-07-23 | 深圳鱼亮科技有限公司 | Noise reduction pickup system and method based on USB |
| CN113163282B (en) * | 2021-03-31 | 2023-12-29 | 深圳鱼亮科技有限公司 | Noise reduction pickup system and method based on USB |
| CN114007157A (en) * | 2021-10-28 | 2022-02-01 | 中北大学 | An intelligent noise-cancelling communication headset |
| CN114153314B (en) * | 2021-11-29 | 2023-04-25 | 重庆长安汽车股份有限公司 | In-vehicle noise dynamic display interaction method and system for enhancing user experience |
| CN114153314A (en) * | 2021-11-29 | 2022-03-08 | 重庆长安汽车股份有限公司 | In-vehicle noise dynamic display interaction method and system for enhancing user experience |
| CN114255779A (en) * | 2021-12-17 | 2022-03-29 | 思必驰科技股份有限公司 | Audio noise reduction method, electronic device and storage medium for VR device |
| CN115831110A (en) * | 2022-11-02 | 2023-03-21 | 广东美的厨房电器制造有限公司 | Noise reduction method, electronic device and storage device |
| CN119763564A (en) * | 2024-11-22 | 2025-04-04 | 成都理工大学 | Embedded speech recognition control module and its device interaction system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112053701A (en) | Sound pickup control method, sound pickup control apparatus, sound pickup control system, sound pickup device, and sound pickup medium | |
| CN109920419B (en) | Voice control method and device, electronic equipment and computer readable medium | |
| RU2461081C2 (en) | Intelligent gradient noise reduction system | |
| US20210035563A1 (en) | Per-epoch data augmentation for training acoustic models | |
| EP1208563B1 (en) | Noisy acoustic signal enhancement | |
| US20080147411A1 (en) | Adaptation of a speech processing system from external input that is not directly related to sounds in an operational acoustic environment | |
| US11488617B2 (en) | Method and apparatus for sound processing | |
| CN108681440A (en) | A kind of smart machine method for controlling volume and system | |
| KR20200132613A (en) | Method and apparatus for speech recognition with wake on voice | |
| CN111415653B (en) | Method and device for recognizing speech | |
| CN118800268B (en) | Voice signal processing method, voice signal processing device and storage medium | |
| EP3792918B1 (en) | Digital automatic gain control method and apparatus | |
| CN111722696B (en) | Voice data processing method and device for low-power-consumption equipment | |
| CN111048118B (en) | Voice signal processing method and device and terminal | |
| CN105427866A (en) | Voice processing method and device, and pickup circuit | |
| CN106782586B (en) | Audio signal processing method and device | |
| CN112312258B (en) | Intelligent earphone with hearing protection and hearing compensation | |
| CN108962226B (en) | Method and apparatus for detecting end point of voice | |
| CN116884405A (en) | Speech instruction recognition method, device and readable storage medium | |
| US9978393B1 (en) | System and method for automatically removing noise defects from sound recordings | |
| CN113889116A (en) | Voice information processing method and device, storage medium and electronic device | |
| CN111383629B (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN118972771A (en) | A sound testing and automatic tuning method and system | |
| CN111968620B (en) | Algorithm testing method and device, electronic equipment and storage medium | |
| CN111462757A (en) | Data processing method and device based on voice signal, terminal 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 |