CN117714960A - Detection method and detection device for microphone module, vehicle and storage medium - Google Patents
Detection method and detection device for microphone module, vehicle and storage medium Download PDFInfo
- Publication number
- CN117714960A CN117714960A CN202311699634.6A CN202311699634A CN117714960A CN 117714960 A CN117714960 A CN 117714960A CN 202311699634 A CN202311699634 A CN 202311699634A CN 117714960 A CN117714960 A CN 117714960A
- Authority
- CN
- China
- Prior art keywords
- frequency domain
- microphone
- domain signal
- feature
- module
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 230000005236 sound signal Effects 0.000 claims abstract description 61
- 238000012545 processing Methods 0.000 claims abstract description 44
- 238000004364 calculation method Methods 0.000 claims abstract description 29
- 238000000605 extraction Methods 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 description 7
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Abstract
The application discloses a detection method, a detection device, a vehicle and a storage medium of a microphone module. The microphone module comprises a first microphone and a second microphone, the detection method is used for a vehicle, and the detection method comprises the following steps: respectively acquiring audio signals through a first microphone and a second microphone; respectively analyzing and processing the audio signals acquired by the first microphone and the second microphone to generate a first frequency domain signal and a second frequency domain signal; respectively carrying out feature extraction processing on the first frequency domain signal and the second frequency domain signal to generate a first frequency domain feature and a second frequency domain feature; performing correlation calculation according to the first frequency domain feature and the second frequency domain feature to generate a first correlation coefficient; performing correlation calculation according to the first frequency domain signal and the second frequency domain signal to generate a second correlation coefficient; and determining whether the consistency of the microphone module is qualified according to the first correlation coefficient and the second correlation coefficient.
Description
Technical Field
The present disclosure relates to the field of vehicle technologies, and in particular, to a method for detecting a microphone module, a device for detecting a microphone module, a vehicle, and a computer readable storage medium.
Background
A Microphone Array (Microphone Array) is a system consisting of a number of acoustic sensors, typically microphones, for sampling and processing the spatial characteristics of the sound field.
In order to ensure that the performance difference among the microphones does not affect the quality of sound collection when the microphone array collects sound, consistency detection is required to be carried out on the microphone array, currently, the known sound sources are used for playing at fixed positions, signals of microphone elements of the microphone array are collected, indexes such as frequency response of the signals are compared by manual operation through audio analysis software, and therefore consistency among the microphones is judged. However, this scheme is cumbersome in analysis steps and, depending on labor, is difficult to apply to mass production, and, in addition, it is difficult to realize real-time detection of consistency between individual microphones.
Disclosure of Invention
In view of the above, the present application provides a method for detecting a microphone module, a device for detecting a microphone module, a vehicle, and a non-volatile computer-readable storage medium.
The detection method of the microphone module of the embodiment is used for a vehicle, the microphone module comprises a first microphone and a second microphone, and the detection method comprises the following steps:
respectively acquiring audio signals through the first microphone and the second microphone;
respectively analyzing and processing the audio signals acquired by the first microphone and the audio signals acquired by the second microphone to generate a first frequency domain signal and a second frequency domain signal;
performing feature extraction processing on the first frequency domain signal and the second frequency domain signal respectively to generate a first frequency domain feature and a second frequency domain feature, wherein the dimensions of the first frequency domain feature and the second frequency domain feature are equal and smaller than those of the first frequency domain signal;
performing correlation calculation according to the first frequency domain features and the second frequency domain features to generate a first correlation coefficient;
performing correlation calculation according to the first frequency domain signal and the second frequency domain signal to generate a second correlation coefficient;
and determining whether the consistency of the microphone module is qualified according to the first correlation coefficient and the second correlation coefficient.
In some embodiments, the first frequency domain feature and the second frequency domain feature comprise at least one of mel-frequency cepstral coefficients, fbank features, wavelet features.
In some embodiments, the performing feature extraction processing on the first frequency domain signal and the second frequency domain signal to generate a first frequency domain feature and a second frequency domain feature, includes:
filtering the first frequency domain signal and the second frequency domain signal respectively through a filter;
performing logarithmic operation on the filtered first frequency domain signal and the filtered second frequency domain signal respectively to generate a first logarithmic value and a second logarithmic value;
and performing discrete cosine transform processing on the first logarithmic value and the second logarithmic value respectively to generate the first frequency domain feature and the second frequency domain feature.
In some embodiments, the first frequency domain feature and the second frequency domain feature include Fbank features, and the performing feature extraction processing on the first frequency domain signal and the second frequency domain signal to generate a first frequency domain feature and a second frequency domain feature respectively includes:
filtering the first frequency domain signal and the second frequency domain signal respectively through a filter;
and respectively carrying out energy normalization processing on the filtered first frequency domain signal and the filtered second frequency domain signal to generate the first frequency domain feature and the second frequency domain feature.
In some embodiments, determining whether the consistency of the microphone module is acceptable according to the first correlation coefficient and the second correlation coefficient includes:
under the condition that the first correlation coefficient is larger than a first threshold value and the second correlation coefficient is larger than a second threshold value, determining that the consistency of the microphone module is qualified;
and under the condition that the first correlation coefficient is smaller than or equal to a first threshold value and/or the second correlation coefficient is smaller than or equal to a second threshold value, determining that the consistency of the microphone module is disqualified.
In certain embodiments, the detection method further comprises:
and under the condition that the consistency of the microphone module is not qualified, generating a log according to the consistency result of the microphone module.
In some embodiments, the acquiring audio signals by the first microphone and the second microphone, respectively, comprises:
detecting a vehicle-machine state of the vehicle;
and respectively acquiring audio signals through the first microphone and the second microphone after the vehicle body machine of the vehicle is started for a preset time.
In some embodiments, analyzing the user signal acquired by the first microphone and the audio signal acquired by the second microphone respectively to generate a first frequency domain signal and a second frequency domain signal includes:
and respectively carrying out short-time Fourier analysis processing on the user signal acquired by the first microphone and the audio signal acquired by the second microphone to generate the first frequency domain signal and the second frequency domain signal.
The detection device of this application embodiment's microphone module for the vehicle, the microphone module includes first microphone and second microphone, and detection device includes:
the acquisition module is used for respectively acquiring audio signals through the first microphone and the second microphone;
the analysis module is used for respectively analyzing and processing the audio signals acquired by the first microphone and the audio signals acquired by the second microphone to generate a first frequency domain signal and a second frequency domain signal;
the characteristic extraction module is used for carrying out characteristic extraction processing on the first frequency domain signal and the second frequency domain signal respectively to generate a first frequency domain characteristic and a second frequency domain characteristic, and the dimensions of the first frequency domain characteristic and the second frequency domain characteristic are equal and smaller than those of the first frequency domain signal;
the first calculation module is used for carrying out correlation calculation according to the first frequency domain feature and the second frequency domain feature to generate a first correlation coefficient;
the second calculation module is used for carrying out correlation calculation according to the first frequency domain signal and the second frequency domain signal to generate a second correlation coefficient;
and the determining module is used for determining whether the consistency of the microphone module is qualified according to the first correlation coefficient and the second correlation coefficient.
The vehicle of the embodiment of the application comprises a processor and a memory, wherein the memory stores a computer program, and the computer program, when executed by the processor, enables the processor to execute the detection method of the microphone module.
The non-volatile computer readable storage medium of the present application contains a computer program which, when executed by a processor, causes the processor to execute the method for detecting a microphone module
In the detection method, the detection device, the vehicle and the readable storage medium for the microphone module, the audio signals are respectively obtained through the first microphone and the second microphone, the obtained audio signals are respectively analyzed and processed to generate balanced and stable first frequency domain signals and stable second frequency domain signals, the first frequency domain signals and the second frequency domain signals are respectively subjected to feature extraction processing to generate first frequency domain features and second frequency domain features with dimensions smaller than those of the first frequency domain signals and the second frequency domain signals, correlation calculation is carried out according to the first frequency domain features and the second frequency domain features to generate first correlation coefficients, and second correlation coefficients which are different from the dimensions of the first correlation coefficients are obtained according to the first frequency domain signals and the second frequency domain signals.
Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flow chart of a method for detecting a microphone module according to some embodiments of the present application;
FIG. 2 is a block diagram of a detection device of a microphone module according to some embodiments of the present application;
fig. 3-7 are flow diagrams of detection methods according to certain embodiments of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present application and are not to be construed as limiting the present application.
Referring to fig. 1, an embodiment of the present application provides a method for detecting a microphone module, which is used for a vehicle, the microphone module includes a first microphone and a second microphone, and the method includes:
01, respectively acquiring audio signals through a first microphone and a second microphone;
02, respectively analyzing and processing the audio signal acquired by the first microphone and the audio signal acquired by the second microphone to generate a first frequency domain signal and a second frequency domain signal;
03, respectively carrying out feature extraction processing on the first frequency domain signal and the second frequency domain signal to generate a first frequency domain feature and a second frequency domain feature, wherein the dimensions of the first frequency domain feature and the second frequency domain feature are equal and smaller than those of the first frequency domain signal;
04, performing correlation calculation according to the first frequency domain feature and the second frequency domain feature to generate a first correlation coefficient;
05, performing correlation calculation according to the first frequency domain signal and the second frequency domain signal to generate a second correlation coefficient;
06, determining whether the consistency of the microphone module is qualified according to the first correlation coefficient and the second correlation coefficient.
Referring to fig. 2, an embodiment of a detection apparatus 10 for a microphone module is provided. The detection device 10 comprises an acquisition module 11, an analysis module 12, a feature extraction module 13, a first calculation module 14, a second calculation module 15 and a determination module 16. Wherein step 01 may be implemented by the acquisition module 11, step 02 may be implemented by the analysis module 12, step 03 may be implemented by the feature extraction module 13, step 04 may be implemented by the first calculation module 14, step 05 may be implemented by the second calculation module 15, and step 06 may be implemented by the determination module 16.
Alternatively, the acquiring module 11 may be configured to acquire the audio signals through the first microphone and the second microphone, respectively; the analysis module 12 may be configured to perform analysis processing on the audio signal acquired by the first microphone and the audio signal acquired by the second microphone, to generate a first frequency domain signal and a second frequency domain signal, respectively. The feature extraction module 13 may be configured to perform feature extraction processing on the first frequency domain signal and the second frequency domain signal, to generate a first frequency domain feature and a second frequency domain feature, where dimensions of the first frequency domain feature and the second frequency domain feature are equal to and smaller than dimensions of the first frequency domain signal. The first calculating module 14 may be configured to perform correlation calculation according to the first frequency domain feature and the second frequency domain feature, and generate a first correlation coefficient; the second calculating module 15 may be configured to perform correlation calculation according to the first frequency domain signal and the second frequency domain signal, and generate a second correlation coefficient; the determining module 16 may be configured to determine whether the consistency of the microphone module is acceptable based on the first correlation coefficient and the second correlation coefficient.
The application also provides a vehicle, which comprises a microphone module, a processor and a memory, wherein the microphone module comprises a first microphone and a second microphone, the memory stores a computer program, and when the computer program is executed by the processor, the processor is enabled to realize the detection method, namely, the processor is used for respectively acquiring audio signals through the first microphone and the second microphone; respectively analyzing and processing the audio signals acquired by the first microphone and the audio signals acquired by the second microphone to generate a first frequency domain signal and a second frequency domain signal; the first frequency domain signal and the second frequency domain signal are respectively subjected to feature extraction processing to generate a first frequency domain feature and a second frequency domain feature, wherein the dimensions of the first frequency domain feature and the second frequency domain feature are equal and smaller than those of the first frequency domain signal; the processor also carries out correlation calculation according to the first frequency domain feature and the second frequency domain feature to generate a first correlation coefficient; and performing correlation calculation according to the first frequency domain signal and the second frequency domain signal to generate a second correlation coefficient, and determining whether the consistency of the microphone module is qualified according to the first correlation coefficient and the second correlation coefficient.
According to the detection method, the detection device and the vehicle of the microphone module, the audio signals are respectively obtained through the first microphone and the second microphone, the obtained audio signals are respectively analyzed and processed to generate the first frequency domain signals and the second frequency domain signals, so that the frequency spectrum characteristics of the audio signals can be clearly displayed, the frequency components and the energy distribution of the audio signals can be conveniently analyzed, the properties and the characteristics of the audio signals can be better understood, the first frequency domain signals and the second frequency domain signals are respectively subjected to characteristic extraction processing, the first frequency domain characteristics and the second frequency domain characteristics with the dimensions smaller than the first frequency domain signals and the second frequency domain signals are generated, the correlation calculation is carried out according to the first frequency domain characteristics and the second frequency domain characteristics to generate the first correlation coefficients, the second correlation coefficients with the dimensions different from the first correlation coefficients are calculated and obtained, and finally the microphone module is subjected to consistency assessment according to the first correlation coefficients and the second correlation coefficients, the microphone module is better in the consistency assessment, the microphone is better in the consistency state of the microphone module is better in the microphone with the microphone, the microphone is more convenient to estimate the audio signal consistency, the microphone is better in the consistency state of the microphone is better in the microphone and the microphone is more convenient to obtain, the microphone is more convenient to estimate the state of the microphone is better in the microphone, and the microphone is more convenient to use, and has more real time, and more convenient to estimate the user state.
In some embodiments, the detection device 10 may be part of a vehicle. Alternatively, the vehicle includes the detection device 10.
In some embodiments, the detection device 10 may be a discrete component assembled in a manner to have the aforementioned functions, or a chip in the form of an integrated circuit having the aforementioned functions, or a computer software code segment that when run on a computer causes the computer to have the aforementioned functions.
In some embodiments, the detection device 10 may be attached to the vehicle as a stand alone or as an additional peripheral component, as hardware. The detection device 10 may also be integrated into the vehicle, for example, the detection device 10 may be integrated into the processor when the detection device 10 is part of the vehicle.
It should be noted that the audio signal may include, but is not limited to, user voice, all audio in a certain environment or audio in a specific frequency band (music, voice), and the like. That is, the audio signal may be any input audio, and the specific type is not limited. For example, in this embodiment, the audio signal may be in-car audio acquired by turning on the first microphone and the second microphone in the microphone module for a certain period, and it is understood that the audio signals acquired by the first microphone and the second microphone may be different in different periods.
The Microphone module may be in a cabin of a vehicle, and the Microphone module includes a plurality of microphones forming a Microphone Array (Microphone Array), which as will be understood by those skilled in the art is a system that is composed of a number of acoustic sensors (typically microphones) for sampling and processing the spatial characteristics of a sound field. The microphones are arranged according to a certain rule, such as a linear shape, a ring shape and the like, and the collected sound signals in different space directions are subjected to space-time processing through a specific algorithm, so that the functions of noise suppression, reverberation removal, human voice interference suppression, sound source direction finding, sound source tracking, array gain and the like are realized, and the processing quality of the sound signals is further improved, so that the sound recognition rate in a real environment is improved.
The specific number of microphones in the microphone module is not limited, and may be, for example, 2, 3, 4 or more, and in this embodiment, the microphone module includes the first microphone and the second microphone, that is, the microphone module is not limited to include only the first microphone and the second microphone.
When a user or a related technician needs to know the consistency of the microphone modules, the processor can start the first microphone and the second microphone, so that the first microphone and the second microphone can acquire a section of audio signals in real time, further, the audio signals acquired by the first microphone can be respectively subjected to short-time Fourier analysis processing, so that a first frequency domain signal is generated, and the audio signals of the second microphone are subjected to short-time Fourier analysis processing, so that a second frequency domain signal is generated. Thus, the resulting first audio signal and second frequency domain signal are better able to characterize the frequency content and energy distribution of the audio signal.
The first frequency domain signal may be represented by d1 (k, N) and the second frequency domain signal may be represented by d2 (k, N), where k is used to represent the dimension of the frequency domain, the value range is from 0- (N-1), N is the length of the time domain signal, and when k is equal to 0, the direct current component, that is, the average value of the signal, is represented; when k is equal to N/2, the highest frequency of the signal is represented; when k is equal to N-1, the lowest frequency of the signal is represented. n represents the dimension of the time domain for discretizing the signal. In this embodiment, the first frequency domain signal and the second frequency domain signal have dimensions within 40 dimensions, that is, k e (1, 40). Therefore, when the correlation coefficient is calculated according to the first audio signal and the second frequency domain signal, noise (high dimension) interference in the audio signal can be effectively avoided.
The processor can also perform feature extraction on the first frequency domain signal d1 (k, n) and the second frequency domain signal d2 (k, n) to obtain dimensionsA first frequency domain feature and a second frequency domain feature of lower degree. The first frequency domain feature may be C 1 (n) the second frequency domain feature may be represented by C 2 (n) represents a compound. First frequency domain feature C 1 (n) and second frequency-domain feature C 2 The dimensions of (n) are the same and smaller than the dimensions of the first frequency domain signal d1 (k, n). For example, in the present application the first frequency domain feature C 1 (n) and second frequency-domain feature C 2 (n) comprises 2-14 dimensions.
Further, a first frequency domain feature C 1 (n) and second frequency-domain feature C 2 (n) comprises at least one of mel-frequency cepstral coefficient, fbank characteristic, wavelet characteristic. For example, in some examples, the first frequency domain feature and the second frequency domain feature may be mel-frequency cepstral coefficients, and for example, in some examples, the first frequency domain feature and the second frequency domain feature may be Fbank features and wavelet features. It is understood that the first frequency domain feature and the second frequency domain feature may be selected according to the actual scene, and the specific selection is not limited. It should be noted that the Fbank feature is a front-end processing method, which is mainly used for processing an audio signal to extract different frequency components in the audio signal. The computation flow of Fbank features is similar to that of a spectrogram, but the difference is that a Mel filter is added, so that the obtained features are more similar to the characteristics of human ears. The Fbank features can better simulate the perception of the human auditory system to different frequencies, so that the audio features which are more in line with the human auditory perception features are extracted. Mel-frequency cepstral coefficient (Mel-frequency cepstral coefficients, MFCC) is a Discrete Cosine Transform (DCT) based on Fbank features to further extract the most important features. The result after DCT is the MFCC feature. Since the MFCC features employ DCT, better noise immunity and robustness are achieved. The wavelet features may be used to extract information such as spectral characteristics, energy distribution, etc. of the speech signal, thereby improving the accuracy of speech recognition.
Further, after generating the first frequency domain feature and the second frequency domain feature, the processor may calculate a first correlation coefficient according to the first frequency domain feature and the second frequency domain feature, and the calculation expression may be:
wherein ρ is 12 Expressed as a first correlation coefficient, cov denotes the calculated covariance, C 1 (n) represents a first frequency domain feature, C 2 (n) represents a second frequency domain feature, delta 1 Standard deviation, delta, representing a first frequency domain characteristic 2 Representing the standard deviation of the second frequency domain feature.
The processor may also calculate a second correlation coefficient from the first frequency domain signal and the second frequency domain signal, and the calculation expression may be:
wherein ρ_freq 12 Representing a second correlation coefficient, cov represents the calculated covariance, d 1 (n) represents a first frequency domain signal, d 2 (n) represents a second frequency domain signal, delta-freq 1 Representing standard deviation of the first frequency domain signal, delta-freq 2 Representing the standard deviation of the second frequency domain signal.
Therefore, after the processor generates the first correlation coefficient and the second correlation coefficient, the first microphone and the second microphone are evaluated from different dimensions according to the first correlation coefficient and the second correlation coefficient, and the influence of noise on consistency judgment is reduced. Therefore, the degree of the consistency state of the microphone module can be better judged, and the technical staff can conveniently and well estimate the interaction state of the whole vehicle and the machine.
Referring to fig. 3, in some embodiments, step 03 includes:
031, filtering the first frequency domain signal and the second frequency domain signal through a filter;
032, respectively carrying out logarithmic operation on the filtered first frequency domain signal and the filtered second frequency domain signal to generate a first logarithmic value and a second logarithmic value;
033, performing discrete cosine transform processing on the first logarithmic value and the second logarithmic value respectively to generate a first frequency domain feature and a second frequency domain feature.
Referring to fig. 2, in some embodiments, the substeps 031-033 may be implemented by the feature extraction module 13, or the feature extraction module 13 may be configured to perform filtering processing on the first frequency domain signal and the second frequency domain signal respectively through a filter, perform logarithmic operation on the filtered first frequency domain signal and the filtered second frequency domain signal respectively to generate a first logarithmic value and a second logarithmic value, and perform discrete cosine transform processing on the first logarithmic value and the second logarithmic value respectively to generate a first frequency domain feature and a second frequency domain feature.
In some embodiments, the processor may be configured to filter the first frequency domain signal and the second frequency domain signal, respectively, perform a logarithmic operation on the filtered first frequency domain signal and second frequency domain signal, respectively, to generate a first logarithmic value and a second logarithmic value, and perform a discrete cosine transform process on the first logarithmic value and the second logarithmic value, respectively, to generate a first frequency domain feature and a second frequency domain feature.
It should be noted that, in the embodiment of the present application, the first frequency domain feature and the second frequency domain feature may be mel frequency cepstrum coefficients, and the filter may be a mel filter.
In sub-step 031, the calculation formula for the filtering process may be:
wherein H is m (k) For the filtering result, m is the number of mel filters, f (m) is the frequency domain signal, and k is the short-time fourier analysis frequency point.
In sub-step 032, the computational expression of the logarithmic operation may be:
wherein d i (k, n) is a frequency domain signal, S i (m) is d i Logarithmic energy of (k, n), H m (k) Is the filtering processing result.
In sub-step 033, the calculated expression of mel-cepstral coefficients may be:
wherein, C (n) is the mel-frequency cepstrum coefficient, n is the order of the mel-frequency cepstrum coefficient, and m is the number of the mel-frequency filters.
Referring to fig. 4, in some embodiments, 03 further comprises:
034, filtering the first frequency domain signal and the second frequency domain signal respectively through a filter;
035, performing energy normalization processing on the filtered first frequency domain signal and the second frequency domain signal respectively to generate a first frequency domain feature and a second frequency domain feature.
With further reference to fig. 2, in some embodiments, the substeps 034-035 may be implemented by the feature extraction module 13, or the feature extraction module 13 may be configured to filter the first frequency domain signal and the second frequency domain signal with filters, and perform energy normalization processing on the filtered first frequency domain signal and the filtered second frequency domain signal, respectively, to generate the first frequency domain feature and the second frequency domain feature.
In some embodiments, the processor may be configured to perform filtering processing on the first frequency domain signal and the second frequency domain signal through a filter, and perform energy normalization processing on the filtered first frequency domain signal and the filtered second frequency domain signal, respectively, to generate a first frequency domain feature and a second frequency domain feature.
In this embodiment, the first frequency domain feature and the second frequency domain feature in the embodiment of the present application may be Fbank features, and the filter may be a mel filter.
Specifically, the first frequency domain signal and the second frequency domain signal may be respectively filtered by a triangular filter designed according to Mel scale. Wherein the center frequencies of the filters are equally spaced on the Mel scale, and the bandwidths of the filters increase as the center frequency increases. In this way, the filter bank may be made to better match the perceptual characteristics of the human auditory system.
Referring to fig. 5, in some embodiments, step 06 comprises:
061, determining that the consistency of the microphone module is qualified under the condition that the first correlation coefficient is larger than a first threshold value and the second correlation coefficient is larger than a second threshold value; or (b)
062, determining that the consistency of the microphone module is not qualified under the condition that the first correlation coefficient is smaller than or equal to a first threshold value and/or the second correlation coefficient is smaller than or equal to a second threshold value.
Referring further to fig. 2, in some embodiments, substeps 061 and 062 may be implemented by the determining module 16, or the determining module 16 is configured to determine that the microphone module consistency is acceptable if the first correlation coefficient is greater than a first threshold and the second correlation coefficient is greater than a second threshold; or under the condition that the first correlation coefficient is smaller than or equal to a first threshold value and/or the second correlation coefficient is smaller than or equal to a second threshold value, determining that the consistency of the microphone module is disqualified.
In some embodiments, the processor is configured to determine that the microphone module consistency is acceptable if the first correlation coefficient is greater than a first threshold and the second correlation coefficient is greater than a second threshold; or under the condition that the first correlation coefficient is smaller than or equal to a first threshold value and/or the second correlation coefficient is smaller than or equal to a second threshold value, determining that the consistency of the microphone module is disqualified.
It should be noted that when the first microphone and the second microphone have good consistency, the first correlation coefficient and the second correlation coefficient may be relatively high, when the microphone has poor consistency, the second correlation coefficient may be relatively low, and the first correlation coefficient is relatively insensitive, and when the microphone has serious consistency, the first correlation coefficient and the second correlation coefficient are relatively low, which represents that the audio signals obtained by the two microphones cannot be used as input of a subsequent module. Thus, by setting a first threshold and a second threshold, and comparing the first correlation coefficient with the first threshold and the second correlation coefficient with the second threshold, respectively, the degree of consistency between microphones may be determined.
Referring to fig. 6, in some embodiments, the detection method further includes:
and 07, generating a log according to the consistency result of the microphone module when the consistency of the microphone module is not qualified.
Referring to fig. 2, in some embodiments, the detecting apparatus 10 further includes a generating module 17, and step 07 may be implemented by the generating module 17, or the generating module 17 may be configured to generate a log according to the consistency result of the microphone module when the consistency of the microphone module is not qualified.
In some embodiments, the processor may be further configured to generate a log based on the consistency result of the microphone module in the event that the consistency of the microphone module is not acceptable.
Therefore, the method and the system facilitate relevant technicians to grasp whether the microphone module has the consistency problem through the log, and the relevant technicians can repair the microphone module with the consistency problem in a targeted manner.
Referring to fig. 7, in some embodiments, step 01 includes:
011, detecting the state of a vehicle;
012, respectively acquiring audio signals through the first microphone and the second microphone after the vehicle machine of the vehicle is started for a preset time.
In some embodiments, the acquiring module 11 may be further configured to detect a state of a vehicle machine of the vehicle, and acquire the audio signals through the first microphone and the second microphone after the vehicle machine of the vehicle is started for a preset time.
In some embodiments, the processor may be further configured to detect a state of a vehicle and acquire the audio signals through the first microphone and the second microphone, respectively, after a preset time of starting the vehicle.
Specifically, the vehicle state may be a start state and a stop state, and when it is detected that the vehicle state is changed from the stop state to the start state, the first microphone and the second microphone are started to acquire audio signals respectively after a preset time. Wherein the preset time may be 4 seconds, 5 seconds, 6 seconds, 7 seconds, 10 seconds or more. For example, in this embodiment, the preset time may be 6 seconds.
It can be appreciated that, since the continuous monitoring occupies a certain computing resource during the use of the vehicle, the audio signal is acquired by setting the first 6 seconds of the start of the vehicle and the consistency of the microphone is detected according to the audio signal, so that the waste of resources can be reduced.
The embodiments also provide a non-volatile computer readable storage medium storing a computer program, which when executed by a processor, causes the processor to perform the above-described detection method.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (11)
1. A method of detecting a microphone module for a vehicle, the microphone module comprising a first microphone and a second microphone, the method comprising:
respectively acquiring audio signals through the first microphone and the second microphone;
respectively analyzing and processing the audio signals acquired by the first microphone and the audio signals acquired by the second microphone to generate a first frequency domain signal and a second frequency domain signal;
performing feature extraction processing on the first frequency domain signal and the second frequency domain signal respectively to generate a first frequency domain feature and a second frequency domain feature, wherein the dimensions of the first frequency domain feature and the second frequency domain feature are equal and smaller than those of the first frequency domain signal;
performing correlation calculation according to the first frequency domain features and the second frequency domain features to generate a first correlation coefficient;
performing correlation calculation according to the first frequency domain signal and the second frequency domain signal to generate a second correlation coefficient;
and determining whether the consistency of the microphone module is qualified according to the first correlation coefficient and the second correlation coefficient.
2. The method of claim 1, wherein the first frequency domain feature and the second frequency domain feature comprise at least one of mel-frequency cepstral coefficients, fbank features, wavelet features.
3. The method according to claim 1, wherein the performing feature extraction processing on the first frequency domain signal and the second frequency domain signal to generate a first frequency domain feature and a second frequency domain feature includes:
filtering the first frequency domain signal and the second frequency domain signal respectively through a filter;
performing logarithmic operation on the filtered first frequency domain signal and the filtered second frequency domain signal respectively to generate a first logarithmic value and a second logarithmic value;
and performing discrete cosine transform processing on the first logarithmic value and the second logarithmic value respectively to generate the first frequency domain feature and the second frequency domain feature.
4. The detection method according to claim 2, wherein the first frequency domain feature and the second frequency domain feature include Fbank features, and the performing feature extraction processing on the first frequency domain signal and the second frequency domain signal to generate a first frequency domain feature and a second frequency domain feature respectively includes:
filtering the first frequency domain signal and the second frequency domain signal respectively through a filter;
and respectively carrying out energy normalization processing on the filtered first frequency domain signal and the filtered second frequency domain signal to generate the first frequency domain feature and the second frequency domain feature.
5. The method of detecting according to claim 1, wherein determining whether the consistency of the microphone module is acceptable according to the first correlation coefficient and the second correlation coefficient comprises:
under the condition that the first correlation coefficient is larger than a first threshold value and the second correlation coefficient is larger than a second threshold value, determining that the consistency of the microphone module is qualified;
and under the condition that the first correlation coefficient is smaller than or equal to a first threshold value and/or the second correlation coefficient is smaller than or equal to a second threshold value, determining that the consistency of the microphone module is disqualified.
6. The method of detecting according to claim 5, further comprising:
and under the condition that the consistency of the microphone module is not qualified, generating a log according to the consistency result of the microphone module.
7. The method of detecting according to claim 1, wherein the acquiring audio signals by the first microphone and the second microphone, respectively, includes:
detecting a vehicle-machine state of the vehicle;
and respectively acquiring audio signals through the first microphone and the second microphone after the vehicle body machine of the vehicle is started for a preset time.
8. The detection method according to claim 1, wherein analyzing the user signal acquired by the first microphone and the audio signal acquired by the second microphone respectively to generate a first frequency domain signal and a second frequency domain signal includes:
and respectively carrying out short-time Fourier analysis processing on the user signal acquired by the first microphone and the audio signal acquired by the second microphone to generate the first frequency domain signal and the second frequency domain signal.
9. A detection apparatus for a microphone module for a vehicle, the microphone module including a first microphone and a second microphone, the detection apparatus comprising:
the acquisition module is used for respectively acquiring audio signals through the first microphone and the second microphone;
the analysis module is used for respectively analyzing and processing the audio signals acquired by the first microphone and the audio signals acquired by the second microphone to generate a first frequency domain signal and a second frequency domain signal;
the characteristic extraction module is used for carrying out characteristic extraction processing on the first frequency domain signal and the second frequency domain signal respectively to generate a first frequency domain characteristic and a second frequency domain characteristic, and the dimensions of the first frequency domain characteristic and the second frequency domain characteristic are equal and smaller than those of the first frequency domain signal;
the first calculation module is used for carrying out correlation calculation according to the first frequency domain feature and the second frequency domain feature to generate a first correlation coefficient;
the second calculation module is used for carrying out correlation calculation according to the first frequency domain signal and the second frequency domain signal to generate a second correlation coefficient;
and the determining module is used for determining whether the consistency of the microphone module is qualified according to the first correlation coefficient and the second correlation coefficient.
10. A vehicle comprising a processor and a memory, the memory storing a computer program which, when executed by the processor, causes the processor to perform the method of detecting a microphone module according to any of claims 1-8.
11. A non-transitory computer readable storage medium containing a computer program, characterized in that the computer program, when executed by a processor, causes the processor to perform the method of detecting a microphone module according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311699634.6A CN117714960A (en) | 2023-12-11 | 2023-12-11 | Detection method and detection device for microphone module, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311699634.6A CN117714960A (en) | 2023-12-11 | 2023-12-11 | Detection method and detection device for microphone module, vehicle and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117714960A true CN117714960A (en) | 2024-03-15 |
Family
ID=90149240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311699634.6A Pending CN117714960A (en) | 2023-12-11 | 2023-12-11 | Detection method and detection device for microphone module, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117714960A (en) |
-
2023
- 2023-12-11 CN CN202311699634.6A patent/CN117714960A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106486131B (en) | A kind of method and device of speech de-noising | |
| CN108701469B (en) | Cough sound recognition method, device, and storage medium | |
| US8140331B2 (en) | Feature extraction for identification and classification of audio signals | |
| CN109313909B (en) | Method, device, apparatus and system for evaluating consistency of microphone array | |
| CN110880329B (en) | Audio identification method and equipment and storage medium | |
| CN108766454A (en) | A kind of voice noise suppressing method and device | |
| CN108847253B (en) | Vehicle model identification method, device, computer equipment and storage medium | |
| Pillos et al. | A Real-Time Environmental Sound Recognition System for the Android OS. | |
| WO2013164029A1 (en) | Detecting wind noise in an audio signal | |
| CN111640411B (en) | Audio synthesis method, device and computer readable storage medium | |
| US9792898B2 (en) | Concurrent segmentation of multiple similar vocalizations | |
| AU2022275486A1 (en) | Methods and apparatus to fingerprint an audio signal via normalization | |
| Chu et al. | A noise-robust FFT-based auditory spectrum with application in audio classification | |
| CN111968651A (en) | WT (WT) -based voiceprint recognition method and system | |
| CN115223584B (en) | Audio data processing method, device, equipment and storage medium | |
| CN117714960A (en) | Detection method and detection device for microphone module, vehicle and storage medium | |
| CN110767238B (en) | Blacklist identification method, device, equipment and storage medium based on address information | |
| CN113593604A (en) | Method, device and storage medium for detecting audio quality | |
| CN112118511A (en) | Earphone noise reduction method and device, earphone and computer readable storage medium | |
| JP4249697B2 (en) | Sound source separation learning method, apparatus, program, sound source separation method, apparatus, program, recording medium | |
| CN116453537B (en) | Method and system for improving audio information transmission effect | |
| CN115691556B (en) | Method for detecting multichannel voice quality of equipment side | |
| Singh | pyAudioProcessing: Audio Processing, Feature Extraction, and Machine Learning Modeling. | |
| US20240000369A1 (en) | AUTOMATIC PARKINSONS DISEASE DETECTION BASED ON THE COMBINATION OF LONG-TERM ACOUSTIC FEATURES AND MEL FREQUENCY COEFFICIENTS (MFCCs) | |
| TW201142820A (en) | Acoustical wave identification system and the method thereof |
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 |