CN113870879A - Sharing method of microphone of intelligent household appliance, intelligent household appliance and readable storage medium - Google Patents
Sharing method of microphone of intelligent household appliance, intelligent household appliance and readable storage medium Download PDFInfo
- Publication number
- CN113870879A CN113870879A CN202010536410.3A CN202010536410A CN113870879A CN 113870879 A CN113870879 A CN 113870879A CN 202010536410 A CN202010536410 A CN 202010536410A CN 113870879 A CN113870879 A CN 113870879A
- Authority
- CN
- China
- Prior art keywords
- signal
- audio
- audio information
- amplitude
- microphone
- 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 51
- 230000003595 spectral effect Effects 0.000 claims abstract description 16
- 230000005236 sound signal Effects 0.000 claims description 24
- 238000001228 spectrum Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 10
- 230000009467 reduction Effects 0.000 claims description 9
- 230000000875 corresponding effect Effects 0.000 description 22
- 238000004891 communication Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 230000003993 interaction Effects 0.000 description 8
- 230000006872 improvement Effects 0.000 description 6
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G10L15/00—Speech recognition
- G10L15/04—Segmentation; Word boundary detection
-
- 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
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
-
- 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
- G10L2021/02087—Noise filtering the noise being separate speech, e.g. cocktail party
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention discloses a sharing method of an intelligent household appliance microphone, an intelligent household appliance and a readable storage medium, wherein the method comprises the steps of processing and calculating audio information picked up by a plurality of microphones, calculating the original amplitude, the spectral density, the average processed amplitude and the signal-to-noise ratio of the audio information through weighted dot product to obtain the confidence value of each audio information, and using the audio information of microphone equipment with the highest confidence value.
Description
Technical Field
The invention relates to the field of noise reduction, in particular to a sharing method of an intelligent household appliance microphone, an intelligent household appliance and a readable storage medium.
Background
The smart home often has a voice interaction scene, and a user sends a voice instruction at home, and then the smart device makes a corresponding action. The voice interaction relates to the capture of a voice command by a microphone, the microphones of different devices are generally independent of each other, the position of a user at home is generally not fixed, when the user is far away from a target device needing the voice interaction, or when the user is at any position at home, in extreme, when the user sends the voice command when moving at home, the existing device cannot meet the requirement, the user needs to send the command to the microphone of the target device as far as possible, inconvenience exists in use, and the use experience of the user is reduced.
Disclosure of Invention
To solve the problems in the prior art, an object of the present invention is to provide a method for sharing a microphone of an intelligent home appliance, and a readable storage medium.
In order to achieve the above object, an embodiment of the present invention provides a method for sharing an intelligent microphone of a home appliance, including the following steps:
acquiring audio information picked up by a plurality of microphones;
determining a corresponding frequency spectrum and an energy spectrum according to each piece of audio information, and determining an original amplitude value corresponding to the frequency spectrum and a spectral density corresponding to the energy spectrum;
determining voice information corresponding to each audio information by utilizing noise reduction processing and endpoint detection;
calculating the average amplitude and the signal-to-noise ratio corresponding to each piece of voice information;
calculating the original amplitude, the spectral density, the average amplitude and the signal-to-noise ratio of each piece of audio information and the respective corresponding weighted value dot product to obtain a confidence value of each piece of audio information;
and setting the microphone corresponding to the audio information with the highest confidence value as the preferred microphone.
As a further improvement of the present invention, the audio information includes a direct audio signal, an echo signal, a reverberation signal, and a bottom noise frequency signal, and the energy spectrum is set to be an energy spectrum of the direct audio signal.
As a further improvement of the present invention, the original amplitude includes an audio amplitude of the direct audio signal, an audio amplitude of the echo signal, an audio amplitude of the reverberation signal, and an audio amplitude of the bottom noise signal.
As a further improvement of the invention, the method also comprises the following steps:
and when the audio amplitude of the direct audio signal of any audio information is higher than the minimum amplitude preset value, calculating a confidence value for the audio information dot product.
As a further improvement of the present invention, the ratio of the audio amplitude of the direct audio signal, the spectral density, the audio amplitude of the echo signal, the audio amplitude of the reverberation signal, and the audio amplitude of the bottom noise audio signal is 2:2:1:1: 1.
As a further refinement of the invention, the ratio of the audio amplitude of the direct audio signal, the average amplitude and the weight of the signal-to-noise ratio is 2:8: 5.
As a further improvement of the invention, the method also comprises the following steps:
and carrying out voice recognition on the audio information picked up by the preferred microphone.
As a further improvement of the invention, the method also comprises the following steps:
and when the signal-to-noise ratio of any audio information is lower than the minimum signal-to-noise ratio preset value, excluding the audio information corresponding to the signal-to-noise ratio.
To achieve one of the above objects, an embodiment of the present invention provides an intelligent home appliance, including:
a receiving module for receiving audio information
A memory storing a computer program;
and the processor can realize the steps in the sharing method of the intelligent household appliance microphone when executing the computer program.
In order to achieve one of the above objects, an embodiment of the present invention provides a readable storage medium, which stores a computer program, and the computer program, when executed by a processor, can implement the steps in the method for sharing an intelligent household microphone.
Compared with the prior art, the invention has the following beneficial effects: the method comprises the steps of processing and calculating audio information picked up by a plurality of microphones, calculating the original amplitude, the spectral density, the average amplitude after processing and the signal-to-noise ratio of the audio information through weighted dot products, obtaining the confidence value of each audio information, and finding out the audio information which can reflect the actual voice information of a user most from the plurality of microphones by adopting the audio information of the microphone equipment with the highest confidence value, so that the plurality of microphones at the user can work cooperatively, and the problems that the microphones are far away from the user, and the noise near some microphones is large, so that voice interaction cannot be further performed are solved.
Drawings
Fig. 1 is a flowchart of a method for sharing a microphone of an intelligent home appliance according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a control module according to an embodiment of the invention.
Fig. 3 is a schematic view of a selected scene of a microphone according to an embodiment of the invention.
Wherein: 10. a refrigerator; 11. a memory; 12. a processor; 13. a receiving module; 14. a communication bus; e1, smart television; e2, intelligent air conditioner; e3, intelligent sound box; e4, smart lights; p1, usera; p2, user B; p3, user c.
Detailed Description
The present invention will be described in detail below with reference to specific embodiments shown in the drawings. These embodiments are not intended to limit the present invention, and structural, methodological, or functional changes made by those skilled in the art according to these embodiments are included in the scope of the present invention.
An embodiment of the invention provides a sharing method of an intelligent household appliance microphone, an intelligent household appliance and a readable storage medium.
Fig. 1 is a method for sharing an intelligent household microphone according to an embodiment of the present application, and although the present application provides the method operation steps described in the following embodiments or flowcharts, the method performs the steps in which the necessary causal relationship does not logically exist, based on the conventional or non-creative work, and the execution sequence of the steps is not limited to the execution sequence provided in the embodiments of the present application.
Specifically, the method comprises the following steps:
step 101: acquiring audio information picked up by a plurality of microphones;
here, a plurality of electronic devices supporting voice functions, such as smart speakers, mobile phones, remote controllers, and other intelligent devices supporting voice interaction, such as smart refrigerators, are generally provided in a home, and the intelligent devices are distributed at various locations in the home to obtain audio information received by microphones of the devices, such as audio information of 4 microphones shown in fig. 2.
Step 102: determining a corresponding frequency spectrum and an energy spectrum according to each piece of audio information, and determining an original amplitude value corresponding to the frequency spectrum and a spectral density corresponding to the energy spectrum;
here, the voice command sent by the user is generally a signal with a finite length and no periodicity, so that the voice command can be analyzed in the form of an energy spectrum, the density of the energy spectrum describes the distribution of the energy of the signal along with the frequency, and the distribution of the energy of the voice signal at each frequency point is reflected by calculating the spectral density of the signal.
The original amplitude reflects the strength of the audio signal, and a larger amplitude reflects the strength of the sound signal received by the audio signal at some frequencies, but for a segment of a voice command, different microphones may have points with higher respective amplitudes at different frequencies.
Step 103: determining voice information corresponding to each audio information by utilizing noise reduction processing and endpoint detection;
step 104: calculating the average amplitude and the signal-to-noise ratio corresponding to each piece of voice information;
after the audio information is preprocessed, in order to make the audio more clear and convenient to process, operations of noise reduction and endpoint detection are required, and then an average amplitude and a signal-to-noise ratio of the processed audio are calculated, wherein the average amplitude represents the overall intensity of the voice received by the microphone in the whole voice command process, and the signal-to-noise ratio is the ratio of the voice information to the background noise, and the larger the ratio is, the higher the reliability of the voice information is.
In addition, the above-mentioned judgment of the audio information mainly includes two steps, namely preprocessing the audio information and analyzing the information after noise reduction and endpoint detection of the audio information. The noise reduction processing of the audio information is mainly used for removing background noise, and the endpoint detection of the audio information is used for distinguishing the voice instruction information of the user from the environmental background sound. In the process of denoising and removing the background noise of the audio, the voice command itself is inevitably influenced, the background noise cannot be completely removed generally, the more the background noise is removed, the more the content of the voice command part is lost, and the same problem that complete distinction cannot be performed in the process of endpoint detection and the influence is caused on the voice command itself during distinction exists. Therefore, in order to avoid the problem that the voice instruction part in the audio information is lost after the noise reduction and the endpoint detection of the audio information, the audio information is preprocessed, namely, the frequency spectrum and the energy spectrum of the audio information are directly obtained, and the original audio information is judged.
Step 105: calculating the original amplitude, the spectral density, the average amplitude and the signal-to-noise ratio of each piece of audio information and the respective corresponding weighted value dot product to obtain a confidence value of each piece of audio information;
step 106: and setting the microphone corresponding to the audio information with the highest confidence value as the preferred microphone.
When a user sends a voice instruction, a pause may exist in a certain period of speech, and the content before and after the pause is semantically the content of one instruction, but the pause time is generally different from the pause between two instruction information, that is, the pause time in one instruction is generally not long, but at the pause position, the amplitude of the audio frequency is reduced, so that the average amplitude of the whole audio frequency information is reduced, and if the microphones at other positions receive the noise of irrelevant voice instructions, so that the average amplitude is increased, the average amplitude is not favorable for ensuring the reliability of the audio frequency information received by the microphones only by the average amplitude. Therefore, a confidence value is calculated through the weighted information of the plurality of dimensions and the dot product, the confidence value reflects the reliability of the audio information, and the microphone with the highest reliability to a section of voice instruction is determined from the angles that the received voice instruction has high intensity, low background noise and high overall energy intensity and average amplitude during the moving process of the user.
When a user sends a voice instruction at any position, the audio information detected by the microphones at different positions is different, for example, some microphones are far away from the user, the sampled information is unclear, and the environmental noise near some microphones is large, so that the voice information captured by the microphones cannot be accurately recognized. Therefore, it is necessary to select the audio information with the highest reliability from the audio information picked up by the different microphones.
Further, the audio information includes a direct audio signal, an echo signal, a reverberation signal, and a bottom noise signal, and the energy spectrum is set to be an energy spectrum of the direct audio signal, which affects the quality of the audio after the endpoint detection.
Still further, the original amplitudes include an audio amplitude of the direct audio signal, an audio amplitude of the echo signal, an audio amplitude of the reverberation signal, and an audio amplitude of the bottom noise signal.
The four audio amplitudes all affect the signal-to-noise ratio after endpoint detection and noise reduction to different degrees.
The original amplitude weighted value in step 105 is a value obtained by adding a weight to each of the audio amplitudes and then performing a dot product calculation, where the weight 1 is a weight value corresponding to the spectral density, the weight 2 is a weight value corresponding to the average amplitude, and the weight 3 is a weight value corresponding to the signal-to-noise ratio.
Further, the method also comprises the following steps:
and when the audio amplitude of the direct audio signal of any audio information is higher than the minimum amplitude preset value, calculating a confidence value for the audio information dot product. When the audio amplitude of the direct audio signal of any audio information is lower than the minimum amplitude preset value, the microphone corresponding to the audio information may be too far away from the user and does not receive a voice instruction with proper intensity, so in order to reduce the occupation of resources, the audio information of the microphone is not analyzed, and only the audio information of the microphone which is roughly judged to be closer to the user and receives the audio information with higher intensity is processed.
Further, the ratio of the audio amplitude of the direct audio signal, the spectral density, the audio amplitude of the echo signal, the audio amplitude of the reverberation signal, and the audio amplitude of the bottom noise signal is 2:2:1:1: 1.
Further, the ratio of the audio amplitude of the direct audio signal, the average amplitude and the weight of the signal-to-noise ratio is 2:8: 5.
In this embodiment, the confidence value is 10% audio amplitude of the direct audio signal + 10% spectral density + 5% audio amplitude of the echo signal + 5% audio amplitude of the reverberation signal + 5% audio amplitude of the bottom noise signal + 40% average amplitude + 25% signal to noise ratio, and the selection of the preferred microphone is a probability problem, and the weight is also assigned in a probability form to an index with a larger influence factor, and the reliability of the confidence value is higher in such weight assignment through experimental simulation and presetting of some empirical values.
After the proper microphone is selected as the preferred microphone, the voice recognition of the audio information picked up by the preferred microphone is used for voice interaction with the user, the voice recognition of the audio information of the selected microphone can be carried out, and the voice instruction in the voice information is analyzed to carry out more intelligent operation.
In addition, the method also comprises the following steps:
and when the signal-to-noise ratio of any audio information is lower than the minimum signal-to-noise ratio preset value, excluding the audio information corresponding to the signal-to-noise ratio. When the signal-to-noise ratio is too low, the quality of the detected audio information is not high, or the noise is too high, which reflects that the audio information can not well reflect a voice command, in order to avoid making wrong feedback and reduce the waste of resources as much as possible, the content of the audio information with the too low signal-to-noise ratio is not judged more, and only the audio with the signal-to-noise ratio higher than the preset value of the lowest signal-to-noise ratio is analyzed.
To achieve one of the above objects, an embodiment of the present invention provides an intelligent home appliance, a schematic module diagram of which is shown in fig. 2, including:
a receiving module 13 for receiving audio information;
a memory 11 storing a computer program;
the processor 12, when executing the computer program, may implement any one of the steps in the method for sharing an intelligent household appliance microphone, that is, implement the steps in any one of the technical solutions of the method for sharing an intelligent household appliance microphone.
In addition, the intelligent appliance may further include a communication bus 14, where the communication bus 14 is used for establishing a connection between the receiving module 13, the processor 12 and the memory 11, and the communication bus 14 may include a path for transmitting information among the receiving module 13, the processor 12 and the memory 11.
The receiving module 13, using any transceiver or the like, is used for communication with other devices or communication networks, such as ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc. The memory 11 may be self-contained and coupled to the processor 12 via a communication bus 14. The memory 11 may also be integrated with the processor 12. Processor 12 may be a general purpose Central Processing Unit (CPU), microprocessor, Application Specific Integrated Circuit (ASIC), or one or more integrated circuits for controlling the execution of programs in accordance with the teachings of the present application.
In this embodiment, the intelligent appliance may be set as a refrigerator 10, the receiving module 13, the processor 12, the memory 11 and the communication bus 14 are all integrated on the refrigerator 10, the refrigerator 10 receives audio information collected by microphones of other devices through the receiving module 13, and analyzes and processes the audio information by the sharing method of the microphones, or the receiving module 13 on the refrigerator 10 receives audio information of the microphones of each device, processes the audio information by the control method of the sharing microphones, and determines that the most reliable microphone device performs other intelligent operations.
In order to achieve one of the above objects, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, and the computer program, when being executed by the processor 12, can implement any one of the steps in the method for sharing an intelligent household appliance microphone, that is, the steps in any one of the technical solutions in the method for sharing an intelligent household appliance microphone.
In the foregoing description, it should be understood that the disclosed system, and method may be implemented in other ways. For example, the system embodiments described above are merely illustrative, and for example, a division of device modules is merely a logical division, and an actual implementation may have additional divisions, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, systems or modules, and may be in an electrical, mechanical or other form.
For example, the processor 12 in the present application may be integrated into one processing module, or each of the modules may exist alone physically, or 2 or more than 2 modules may be integrated into one module. The integrated module can be realized in a hardware form, and can also be realized in a form of hardware and a software functional module.
The integrated module implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions for causing a computer system (which may be a personal computer, a server, or a network system) or a processor 12(processor) to execute some steps of the methods according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory 11 (ROM), a Random Access Memory 11 (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Taking a specific scenario as an example, as shown in fig. 3, the smart refrigerator 10, the smart television E1, the smart speaker E3, the smart lamp E4, and the smart air conditioner E2 in the home of the user are all equipped with microphones, and the smart home appliance of the sharing method for processing the smart home appliance microphones is set as the smart refrigerator 10, that is, the processor 12 in the smart refrigerator 10 is used to analyze and process the audio information collected by each smart device, and when the user is at any position in the home, for example, at different positions of the user a P1, the user b P2, and the user c P3, the processing results of the audio information of different smart devices are different.
When a user gives a voice command at any position in the home, for example, a command is given at the position of the user b P2, the sound wave of the voice command is assumed to be received by the microphones of the smart tv E1, the smart sound box E3 and the smart air conditioner E2, the microphones convert the sound wave signal into an electric signal, the three devices transmit the electric signal of the audio information to the processor 12 of the refrigerator 10 in a wired or wireless manner, the processor 12 processes the audio information transmitted by the microphones according to the method shared by the smart home appliance microphones described above, determines the corresponding frequency spectrum and energy spectrum, calculates the original amplitude, spectral density, average amplitude and signal-to-noise ratio of the audio information, calculates a confidence value, determines the microphone with the highest confidence value as the preferred microphone, and assumes that the confidence value of the audio information output by the microphone of the smart tv E1 is the highest, the microphone of the smart tv E1 can better reflect the human voice command information of the user b P2, and performing voice recognition on the audio information of the microphone of the intelligent television E1 and performing further man-machine interaction actions.
Compared with the prior art, the embodiment has the following beneficial effects:
the method comprises the steps of processing and calculating audio information picked up by a plurality of microphones, calculating the original amplitude, the spectral density, the average amplitude after processing and the signal-to-noise ratio of the audio information through weighted dot products, obtaining the confidence value of each audio information, and finding out the audio information which can reflect the actual voice information of a user most from the plurality of microphones by adopting the audio information of the microphone equipment with the highest confidence value, so that the plurality of microphones at the user can work cooperatively, and the problems that the microphones are far away from the user, and the noise near some microphones is large, so that voice interaction cannot be further performed are solved.
It should be understood that although the present description refers to embodiments, not every embodiment contains only a single technical solution, and such description is for clarity only, and those skilled in the art should make the description as a whole, and the technical solutions in the embodiments can also be combined appropriately to form other embodiments understood by those skilled in the art.
The above-listed detailed description is only a specific description of a possible embodiment of the present invention, and they are not intended to limit the scope of the present invention, and equivalent embodiments or modifications made without departing from the technical spirit of the present invention should be included in the scope of the present invention.
Claims (10)
1. A sharing method of an intelligent household appliance microphone is characterized by comprising the following steps:
acquiring audio information picked up by a plurality of microphones;
determining a corresponding frequency spectrum and an energy spectrum according to each piece of audio information, and determining an original amplitude value corresponding to the frequency spectrum and a spectral density corresponding to the energy spectrum;
determining voice information corresponding to each audio information by utilizing noise reduction processing and endpoint detection;
calculating the average amplitude and the signal-to-noise ratio corresponding to each piece of voice information;
calculating the original amplitude, the spectral density, the average amplitude and the signal-to-noise ratio of each piece of audio information and the respective corresponding weighted value dot product to obtain a confidence value of each piece of audio information;
and setting the microphone corresponding to the audio information with the highest confidence value as the preferred microphone.
2. The method as claimed in claim 1, wherein the audio information includes a direct audio signal, an echo signal, a reverberation signal and a bottom noise signal, and the energy spectrum is set as an energy spectrum of the direct audio signal.
3. The method of claim 2, wherein the original amplitudes comprise audio amplitudes of the direct audio signal, the echo signal, the reverberation signal, and the background noise signal.
4. The method for sharing a microphone of an intelligent household appliance according to claim 3, further comprising the steps of:
and when the audio amplitude of the direct audio signal of any audio information is higher than the minimum amplitude preset value, calculating a confidence value for the audio information dot product.
5. The method as claimed in claim 3, wherein the ratio of the audio amplitude of the direct audio signal, the spectral density, the audio amplitude of the echo signal, the audio amplitude of the reverberation signal and the audio amplitude of the bottom noise signal is 2:2:1:1: 1.
6. The method of claim 5, wherein the ratio of the audio amplitude of the direct audio signal to the average amplitude to the weight of the signal-to-noise ratio is 2:8: 5.
7. The method for sharing a microphone of an intelligent household appliance according to claim 1, further comprising the steps of:
and carrying out voice recognition on the audio information picked up by the preferred microphone.
8. The method for sharing a microphone of an intelligent household appliance according to claim 1, further comprising the steps of:
and when the signal-to-noise ratio of any audio information is lower than the minimum signal-to-noise ratio preset value, excluding the audio information corresponding to the signal-to-noise ratio.
9. An intelligent appliance, comprising:
a receiving module for receiving audio information
A memory storing a computer program;
a processor, which when executing the computer program, can implement the steps of the method for sharing an intelligent household appliance microphone according to any one of claims 1 to 8.
10. A readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the method for sharing an intelligent home microphone according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010536410.3A CN113870879A (en) | 2020-06-12 | 2020-06-12 | Sharing method of microphone of intelligent household appliance, intelligent household appliance and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010536410.3A CN113870879A (en) | 2020-06-12 | 2020-06-12 | Sharing method of microphone of intelligent household appliance, intelligent household appliance and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113870879A true CN113870879A (en) | 2021-12-31 |
Family
ID=78980785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010536410.3A Pending CN113870879A (en) | 2020-06-12 | 2020-06-12 | Sharing method of microphone of intelligent household appliance, intelligent household appliance and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113870879A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117215516A (en) * | 2023-09-12 | 2023-12-12 | 深圳市品声科技有限公司 | Interaction method and device based on microphone |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6751588B1 (en) * | 1999-11-23 | 2004-06-15 | Sony Corporation | Method for performing microphone conversions in a speech recognition system |
| CN1643571A (en) * | 2002-03-27 | 2005-07-20 | 艾黎弗公司 | Nicrophone and voice activity detection (vad) configurations for use with communication systems |
| CN1670823A (en) * | 2004-03-17 | 2005-09-21 | 哈曼贝克自动系统股份有限公司 | Method for detecting and reducing noise from a microphone array |
| EP2058797A1 (en) * | 2007-11-12 | 2009-05-13 | Harman Becker Automotive Systems GmbH | Discrimination between foreground speech and background noise |
| CN108989947A (en) * | 2018-08-02 | 2018-12-11 | 广东工业大学 | A kind of acquisition methods and system of moving sound |
| CN110931019A (en) * | 2019-12-06 | 2020-03-27 | 广州国音智能科技有限公司 | Public security voice data acquisition method, device, equipment and computer storage medium |
-
2020
- 2020-06-12 CN CN202010536410.3A patent/CN113870879A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6751588B1 (en) * | 1999-11-23 | 2004-06-15 | Sony Corporation | Method for performing microphone conversions in a speech recognition system |
| CN1643571A (en) * | 2002-03-27 | 2005-07-20 | 艾黎弗公司 | Nicrophone and voice activity detection (vad) configurations for use with communication systems |
| CN1670823A (en) * | 2004-03-17 | 2005-09-21 | 哈曼贝克自动系统股份有限公司 | Method for detecting and reducing noise from a microphone array |
| EP2058797A1 (en) * | 2007-11-12 | 2009-05-13 | Harman Becker Automotive Systems GmbH | Discrimination between foreground speech and background noise |
| CN108989947A (en) * | 2018-08-02 | 2018-12-11 | 广东工业大学 | A kind of acquisition methods and system of moving sound |
| CN110931019A (en) * | 2019-12-06 | 2020-03-27 | 广州国音智能科技有限公司 | Public security voice data acquisition method, device, equipment and computer storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117215516A (en) * | 2023-09-12 | 2023-12-12 | 深圳市品声科技有限公司 | Interaction method and device based on microphone |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10453457B2 (en) | Method for performing voice control on device with microphone array, and device thereof | |
| CN106898348B (en) | Dereverberation control method and device for sound production equipment | |
| CN110211580B (en) | Multi-intelligent-device response method, device, system and storage medium | |
| CN107195305B (en) | Information processing method and electronic equipment | |
| CN111223497A (en) | Nearby wake-up method and device for terminal, computing equipment and storage medium | |
| CN107464565B (en) | Far-field voice awakening method and device | |
| CN112037789A (en) | Equipment awakening method and device, storage medium and electronic device | |
| GB2529288A (en) | Spatial audio database based noise discrimination | |
| CN107966910B (en) | Voice processing method, intelligent sound box and readable storage medium | |
| CN205508398U (en) | Intelligent robot with high in clouds interactive function | |
| CN110875045A (en) | Voice recognition method, intelligent device and intelligent television | |
| CA3163476A1 (en) | Method, server, and client for processing noise | |
| CN113593548A (en) | Awakening method and device of intelligent equipment, storage medium and electronic device | |
| CN112908321A (en) | Device control method, device, storage medium, and electronic apparatus | |
| CN113671846A (en) | Intelligent device control method and device, wearable device and storage medium | |
| CN105719672A (en) | Recording scene mode switching method and recording scene mode switching mode device | |
| CN113329372B (en) | Method, device, equipment, medium and product for vehicle-mounted call | |
| CN113870879A (en) | Sharing method of microphone of intelligent household appliance, intelligent household appliance and readable storage medium | |
| CN109243453A (en) | The processing method and processing device of voice messaging, storage medium, electronic device | |
| CN110224904B (en) | Voice processing method, device, computer readable storage medium and computer equipment | |
| CN108962259B (en) | Processing method and first electronic device | |
| CN116708065A (en) | Low-power consumption Bluetooth voice control method and system in intelligent home environment | |
| CN112466305B (en) | Voice control method and device of water dispenser | |
| US20220272442A1 (en) | Voice processing method, electronic device and readable storage medium | |
| CN109872719A (en) | A kind of stagewise intelligent voice system and its method of speech processing |
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 |