Consistency detection method, device and equipment of microphone array and storage medium

Abstract

The application provides a microphone array consistency detection method and device, equipment and a storage medium, and belongs to the technical field of microphones. The method comprises the following steps: sound collection is performed by a plurality of microphones in a microphone array to obtain audio signals of the plurality of microphones; for each microphone, the spectrum of a target frequency band in the audio signal of the microphone is determined; the spectrum of the target frequency band is divided to obtain a plurality of sub-spectra, one sub-spectrum corresponding to one sub-frequency band; for each second microphone except the first microphone in the plurality of microphones, a consistency detection result between the second microphone and the first microphone is determined based on the difference between the plurality of sub-spectra of the second microphone and the plurality of sub-spectra of the first microphone; and in the case that the consistency detection result between each second microphone and the first microphone is consistent, it is determined that the microphone array is consistent, thereby improving the accuracy of consistency detection of the microphone array.

Description

Technical Field

[0001] This application relates to the field of microphone technology, and in particular to a method, apparatus, device, and storage medium for detecting the consistency of a microphone array. Background Technology

[0002] A microphone array is an audio acquisition device composed of multiple microphones arranged in a specific topology, used to collect audio signals. To ensure the accuracy of the audio signals acquired by the microphone array, it is necessary to detect the consistency of the audio signals collected by the multiple microphones within the array.

[0003] In related technologies, when performing consistency testing on microphone arrays, the average statistical characteristics (such as spectral entropy, amplitude, etc.) among multiple microphones in the array are generally used as a standard. The audio statistical characteristics of an individual microphone are compared with this standard to determine whether the individual microphone meets the consistency criteria, thereby determining whether the microphone array as a whole meets the consistency criteria. However, if there are abnormal microphones in the array, the average statistical characteristics will be inaccurate, resulting in inaccurate consistency testing results. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for microphone array consistency detection, which can improve the accuracy of microphone array consistency detection. The technical solution is as follows:

[0005] On the one hand, a method for detecting the consistency of a microphone array is provided, the method comprising:

[0006] Sound is captured by multiple microphones in a microphone array to obtain the audio signals from the multiple microphones;

[0007] For each microphone, determine the spectrum of the target frequency band in the audio signal of the microphone;

[0008] The spectrum of the target frequency band is divided to obtain multiple sub-spectrums, with each sub-spectrum corresponding to a sub-frequency band.

[0009] For each of the plurality of microphones other than the first microphone, a consistency detection result between the second microphone and the first microphone is determined based on the degree of difference between the plurality of sub-spectrums of the second microphone and the plurality of sub-spectrums of the first microphone, wherein the degree of difference represents the difference between the plurality of sub-spectrums of the second microphone and the plurality of sub-spectrums of the first microphone;

[0010] If the consistency detection results between each second microphone and the first microphone are consistent, the microphone array is determined to be consistent.

[0011] In some embodiments, the method further includes:

[0012] Determine the energy values ​​of each of the multiple sub-spectrums of the first microphone and determine the energy values ​​of each of the multiple sub-spectrums of the second microphone;

[0013] For two sub-spectrums corresponding to the same sub-frequency band in the first microphone and the second microphone, determine the energy difference between the energy values ​​of the two sub-spectrums;

[0014] The number of sub-frequency bands whose absolute value of the energy difference exceeds a first threshold is used as the difference degree.

[0015] In some embodiments, determining the consistency detection result between the second microphone and the first microphone based on the difference between multiple sub-spectrums of the second microphone and multiple sub-spectrums of the first microphone includes:

[0016] If the difference does not exceed the second threshold, the consistency detection result between the second microphone and the first microphone is determined to be consistent.

[0017] In some embodiments, the sound acquisition via a microphone array includes:

[0018] Play Gaussian white noise in the target scene using the target playback device;

[0019] Sound is collected in the target scene using the microphone array.

[0020] In some embodiments, the method further includes:

[0021] The reference distance is determined based on the array aperture of the microphone array and the minimum wavelength of the Gaussian white noise;

[0022] Based on the reference distance, a horizontal distance is determined, wherein the horizontal distance is greater than or equal to the reference distance;

[0023] Based on the first position of the target playback device and the horizontal distance, a second position is determined, and the microphone array is used to collect sound at the second position.

[0024] In some embodiments, after determining that the microphone array conforms to the agreement, the method further includes:

[0025] Based on the audio signals from the multiple microphones, the target playback device is located to obtain an estimated orientation of the target playback device relative to the microphone array;

[0026] If the actual orientation of the target playback device relative to the microphone array matches the estimated orientation, the microphone array is determined to meet the usage requirements.

[0027] In some embodiments, the method further includes:

[0028] The center position is determined based on the positions of each microphone in the microphone array;

[0029] The microphone at the center position is designated as the first microphone.

[0030] In some embodiments, the microphones in the microphone array are each labeled with a different serial number, and the method further includes:

[0031] If the consistency detection result between at least one second microphone and the first microphone is inconsistent, the serial number of the at least one second microphone is output.

[0032] In some embodiments, the method further includes:

[0033] If the number of the at least one second microphone does not exceed a third threshold, the serial number of the at least one second microphone is output.

[0034] In some embodiments, the method further includes:

[0035] If the number of at least one second microphone exceeds a third threshold, a first microphone is re-determined from the plurality of second microphones, and a consistency detection is performed on the microphone array based on the plurality of sub-spectrums of the re-determined first microphone.

[0036] In some embodiments, the method further includes:

[0037] In the case where the microphone array is used for speech detection, the frequency band containing the natural speech frequency in the audio signal is taken as the target frequency band;

[0038] In the case where the microphone array is used for anomaly detection, the frequency band of the audio signal is taken as the target frequency band.

[0039] On the other hand, a microphone array consistency detection device is provided, the device comprising:

[0040] The acquisition module is used to acquire sound through multiple microphones in a microphone array to obtain the audio signals of the multiple microphones;

[0041] The first determining module is used to determine, for each microphone, the spectrum of the target frequency band in the audio signal of the microphone;

[0042] The partitioning module is used to divide the spectrum of the target frequency band to obtain multiple sub-spectrums, with each sub-spectrum corresponding to a sub-frequency band;

[0043] The second determining module is used to determine a consistency detection result between the second microphone and the first microphone for each second microphone other than the first microphone among the plurality of microphones, based on the degree of difference between the plurality of sub-spectrums of the second microphone and the plurality of sub-spectrums of the first microphone, wherein the degree of difference represents the difference between the plurality of sub-spectrums of the second microphone and the plurality of sub-spectrums of the first microphone;

[0044] The third determining module is used to determine that the microphone array is consistent if the consistency detection results between each second microphone and the first microphone are consistent.

[0045] In some embodiments, the apparatus further includes:

[0046] The fourth determining module is used to determine the energy values ​​of each of the multiple sub-spectrums of the first microphone and to determine the energy values ​​of each of the multiple sub-spectrums of the second microphone.

[0047] The fifth determining module is used to determine the energy difference between the energy values ​​of two sub-spectrums corresponding to the same sub-frequency band in the first microphone and the second microphone.

[0048] The sixth determining module is used to take the number of sub-frequency bands whose absolute value of the energy difference corresponding to multiple sub-frequency bands exceeds a first threshold as the difference degree.

[0049] In some embodiments, the second determining module is configured to:

[0050] If the difference does not exceed the second threshold, the consistency detection result between the second microphone and the first microphone is determined to be consistent.

[0051] In some embodiments, the acquisition module is used for:

[0052] Play Gaussian white noise in the target scene using the target playback device;

[0053] Sound is collected in the target scene using the microphone array.

[0054] In some embodiments, the apparatus further includes:

[0055] The seventh determining module is used to determine the reference distance based on the array aperture of the microphone array and the minimum wavelength of the Gaussian white noise;

[0056] The eighth determining module is used to determine the horizontal distance based on the reference distance, wherein the horizontal distance is greater than or equal to the reference distance;

[0057] The ninth determining module is used to determine a second position based on the first position of the target playback device and the horizontal distance, and the microphone array is used to collect sound at the second position.

[0058] In some embodiments, after determining that the microphone array conforms to a consistency standard, the device further includes:

[0059] A positioning module is used to locate the target playback device based on the audio signals from the plurality of microphones, so as to obtain an estimated orientation of the target playback device relative to the microphone array;

[0060] The tenth determining module is used to determine that the microphone array meets the usage requirements when the actual direction of the target playback device relative to the microphone array matches the estimated direction.

[0061] In some embodiments, the apparatus further includes:

[0062] The eleventh determining module is used to determine the center position based on the positions of each microphone in the microphone array;

[0063] The twelfth determining module is used to identify the microphone at the center position as the first microphone.

[0064] In some embodiments, the microphones in the microphone array are each labeled with a different serial number, and the device further includes:

[0065] An output module is configured to output the serial number of the at least one second microphone when the consistency detection result between the at least one second microphone and the first microphone is inconsistent.

[0066] In some embodiments, the output module is further configured to:

[0067] If the number of the at least one second microphone does not exceed a third threshold, the serial number of the at least one second microphone is output.

[0068] In some embodiments, the apparatus further includes:

[0069] The thirteenth determining module is used to redetermine the first microphone from the plurality of second microphones when the number of the at least one second microphone exceeds a third threshold, and to perform consistency detection on the microphone array based on the plurality of sub-spectrums of the redetermined first microphone.

[0070] In some embodiments, the first determining module is configured to:

[0071] In the case where the microphone array is used for speech detection, the frequency band containing the natural speech frequency in the audio signal is taken as the target frequency band;

[0072] In the case where the microphone array is used for anomaly detection, the frequency band of the audio signal is taken as the target frequency band.

[0073] On the other hand, a computer device is provided, the computer device including one or more processors and one or more memories, the one or more memories storing at least one piece of program code, the at least one piece of program code being loaded and executed by the one or more processors to implement the microphone array consistency detection method described in any of the above implementations.

[0074] On the other hand, a computer-readable storage medium is provided, wherein at least one piece of program code is stored in the computer-readable storage medium, the at least one piece of program code being loaded and executed by a processor to implement the microphone array consistency detection method described in any of the above implementations.

[0075] On the other hand, a computer program product is provided, the computer program product including computer program code stored in a computer-readable storage medium, a processor of a computer device reading the computer program code from the computer-readable storage medium, the processor executing the computer program code, causing the computer device to perform the microphone array consistency detection method described in any of the above implementations.

[0076] In this embodiment, the spectrum of the target frequency band in the audio signal of each microphone is divided into multiple sub-spectrums. Since each sub-spectrum can represent a detailed feature of the audio signal, the consistency detection result between the two microphones can be determined based on the difference between the multiple sub-spectrums of each microphone, which can improve the detection accuracy. Furthermore, since the two microphones of a consistent microphone array should be consistent, the consistency between the first microphone and the multiple second microphones is detected separately using the first microphone as a reference standard. If the consistency between each second microphone and the first microphone is consistent, it can be said that the microphone array is consistent, thus improving the accuracy of consistency detection of the microphone array. Attached Figure Description

[0077] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0078] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application;

[0079] Figure 2 This is a flowchart of a microphone array consistency detection method provided in an embodiment of this application;

[0080] Figure 3 This is a flowchart of another microphone array consistency detection method provided in an embodiment of this application;

[0081] Figure 4 This is a flowchart of another microphone array consistency detection method provided in an embodiment of this application;

[0082] Figure 5 This is a block diagram of a microphone array consistency detection device provided in an embodiment of this application;

[0083] Figure 6 This is a block diagram of a control device provided in an embodiment of this application;

[0084] Figure 7 This is a block diagram of a server provided in an embodiment of this application. Detailed Implementation

[0085] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0086] The terms "first," "second," "third," and "fourth," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0087] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the sample data involved in this application were all obtained under full authorization.

[0088] The microphone array consistency detection method provided in this application embodiment can be executed by a computer device. In this application embodiment, the computer device can be configured as a control device or a server. When the computer device is configured as a control device, the control device can act as the execution subject to implement the technical solution provided in this application embodiment. When the computer device is configured as a server, the server can act as the execution subject to implement the technical solution provided in this application embodiment. Alternatively, the technical solution provided in this application can be implemented through interaction between the control device and the server. This application embodiment does not limit this approach. The following uses a computer device as a server as an example to illustrate an implementation environment diagram of the microphone array consistency detection method provided in this application embodiment.

[0089] See Figure 1 The implementation environment includes a microphone array 10 and a server 20. The microphone array 10 is used to collect sound in the conference system and transmit the collected sound data to the server 20. The server 20 transmits the sound data to remote devices participating in the conference. Optionally, a control device 30 can be set up locally. The control device 30 can control the microphone array 10 to collect sound, and the control device 30 can also process the sound data collected by the microphone array 10 before transmitting it to the remote devices through the server 20. In this embodiment, the local control device 30 can detect the transmitted sound data; the control device 30 can also transmit the sound data collected by the microphone array 10 to the server 20 for detection; or, without the control device 30, the server 20 can directly detect the transmitted sound data. This application does not impose specific limitations on this. The microphone array 10, the server 20, and the control device 30 can be directly or indirectly connected via wired or wireless communication. This application does not impose any limitations on this.

[0090] Figure 2 This is a flowchart of a microphone array consistency detection method provided in an embodiment of this application. The method is executed by a computer device and includes:

[0091] 201. Computer equipment acquires sound by using multiple microphones in a microphone array to obtain audio signals from multiple microphones.

[0092] In this embodiment of the application, multiple microphones are arranged in a preset shape to form a microphone array with a topological structure, which may be a linear array, a cross array, a planar array, or a spiral array, etc.

[0093] 202. For each microphone, the computer equipment determines the spectrum of the target frequency band in the microphone's audio signal.

[0094] In this embodiment, each microphone has the same target frequency band. The spectrum of the target frequency band is a frequency domain signal, with the horizontal axis representing frequency and the vertical axis representing amplitude, where amplitude indicates the intensity of the audio signal. The target frequency band can be the frequency band to be detected by the microphone array during application, such as the frequency band corresponding to natural speech frequencies, to ensure the effectiveness of consistency detection of the microphone array based on the spectrum of the target frequency band.

[0095] 203. The computer equipment divides the spectrum of the target frequency band into multiple sub-spectrums, with each sub-spectrum corresponding to a sub-frequency band.

[0096] In this embodiment, the sub-frequency bands of each microphone are also identical. Since these multiple sub-spectrums can represent the detailed features of the audio signal, subsequent consistency detection based on the divided multiple sub-spectrums can improve the detection accuracy.

[0097] 204. For each second microphone other than the first microphone among a plurality of microphones, the computer device determines the consistency detection result between the second microphone and the first microphone based on the difference degree between the plurality of sub-spectrums of the second microphone and the plurality of sub-spectrums of the first microphone, wherein the difference degree represents the difference between the plurality of sub-spectrums of the second microphone and the plurality of sub-spectrums of the first microphone.

[0098] In this embodiment, the consistency detection result is either consistent or inconsistent. In this embodiment, since the difference between the audio signals of two consistent microphones in the microphone array should be small, the consistency between the two microphones is detected based on the difference between the sub-spectrums in their audio signals, ensuring the accuracy of the detection.

[0099] 205. If the consistency detection results between each second microphone and the first microphone are consistent, the computer equipment determines that the microphone array is consistent.

[0100] In this embodiment of the application, if the computer device determines that the microphone array is inconsistent when the consistency detection result between any second microphone and the first microphone is inconsistent, the computer device determines that the microphone array is inconsistent.

[0101] In this embodiment, the spectrum of the target frequency band in the audio signal of each microphone is divided into multiple sub-spectrums. Since each sub-spectrum can represent a detailed feature of the audio signal, the consistency detection result between the two microphones can be determined based on the difference between the multiple sub-spectrums of each microphone, which can improve the detection accuracy. Furthermore, since the two microphones of a consistent microphone array should be consistent, the consistency between the first microphone and the multiple second microphones is detected separately using the first microphone as a reference standard. If the consistency between each second microphone and the first microphone is consistent, it can be said that the microphone array is consistent, thus improving the accuracy of consistency detection of the microphone array.

[0102] Figure 3 This is a flowchart of a microphone array consistency detection method provided in an embodiment of this application. The method is executed by a server and includes:

[0103] 301. The server acquires sound signals from multiple microphones in a microphone array.

[0104] In this embodiment, to ensure the stability of audio signals acquired by multiple microphones, Gaussian white noise is used as the sound source. Accordingly, the process of the server acquiring sound through multiple microphones in the microphone array includes the following steps: the server plays Gaussian white noise in the target scene through the target playback device; the server acquires sound in the target scene through the microphone array.

[0105] In this embodiment, since the energy of Gaussian white noise is uniformly distributed in both the time and frequency dimensions, the audio signals collected by multiple microphones at any time and at any frequency are relatively stable, ensuring the stability of the sound source and thus avoiding detection errors caused by sound source errors.

[0106] It's important to note that sound propagation includes near-field and far-field propagation. In near-field propagation, the sound waveform is a spherical wave, which can cause amplitude differences in the audio signals captured by multiple microphones. In far-field propagation, the sound waveform is a plane wave, and amplitude differences are not a concern. Therefore, to avoid the impact of amplitude differences, far-field propagation can be achieved by controlling the distance between the target playback device and the microphone array. Accordingly, given the location of the target playback device, the server determines the position of the microphone array for sound acquisition through the following steps.

[0107] The server determines a reference distance based on the array aperture of the microphone array and the minimum wavelength of Gaussian white noise; the server determines a horizontal distance based on the reference distance, where the horizontal distance is greater than or equal to the reference distance; the server determines a second position based on the first position of the target playback device and the horizontal distance, and the microphone array is used to collect sound at the second position.

[0108] In this embodiment, the reference distance serves as the boundary between near-field and far-field propagation. If the distance between the target playback device and the microphone array is less than the reference distance, it is considered near-field propagation; if the distance is greater than or equal to the reference distance, it is considered far-field propagation. The horizontal distance refers to the distance between the center positions of the target acquisition device and the microphone array on the same horizontal line. Specifically, the second position refers to the center position of the microphone array, and the first and second positions are located on the same horizontal line.

[0109] The server obtains the horizontal distance using the following formula (1).

[0110]

[0111] In the embodiments of this application, r represents the horizontal distance, D represents the array aperture of the microphone array, and λ represents the minimum wavelength of Gaussian white noise.

[0112] In this implementation, by controlling the distance between the target acquisition device and the microphone array, sound can propagate in the far field between the target acquisition device and the microphone array, thereby avoiding the influence of amplitude differences, reducing the differences between multiple microphones, and thus reducing detection errors.

[0113] In this embodiment, the target scene can be a normal indoor scene, which only needs to be free of obvious interference and noise. This reduces the requirements for the detection scene and enables the detection of the microphone array in a relatively relaxed scene, thereby reducing the detection conditions and improving the universality of the detection.

[0114] 302. For each microphone, the server determines the spectrum of the target frequency band in the microphone's audio signal.

[0115] It should be noted that the audio signals acquired by the microphone array are generally time-domain audio signals. Therefore, before executing step 302, the server needs to perform a Fast Fourier Transform (FFT) on the audio signal to convert the time-domain audio signal into a frequency-domain audio signal, thereby determining the spectrum of the target frequency band in the frequency-domain audio signal. In this embodiment, the horizontal axis of the time-domain audio signal is time, and the vertical axis is amplitude; the horizontal axis of the frequency-domain audio signal is frequency, and the vertical axis is amplitude.

[0116] Because microphone arrays have different response requirements for different frequency bands in audio signals under different application scenarios, the server can determine the target frequency band based on the application scenario of the microphone array. Accordingly, the process of determining the target frequency band by the server includes the following implementation methods: when the microphone array is used for speech detection, the server uses the frequency band containing the natural speech frequency of the audio signal as the target frequency band; when the microphone array is used for anomaly detection, the server uses all frequency bands of the audio signal as the target frequency band. In this implementation method, by using the frequency band containing the natural speech frequency of the audio signal as the target frequency band when the microphone array is used for speech detection, interference from invalid frequency bands such as noise frequency bands is avoided. Furthermore, since the audio signal of an anomaly event may belong to any frequency band, using all frequency bands of the audio signal as the target frequency band allows the microphone array to acquire audio signals from any frequency band in the audio signal, thereby enabling anomaly event detection based on audio signals from any frequency band, ensuring comprehensive detection.

[0117] In this embodiment, various application scenarios of the microphone array and their corresponding frequency bands are stored in a frequency band library, and the microphone array is marked with an application scenario identifier. Accordingly, when the server determines the target frequency band, it first obtains the application scenario identifier of the microphone array to determine the application scenario of the microphone array, and then uses the frequency band corresponding to the application scenario in the frequency band library as the target frequency band, thereby improving the efficiency of determining the target frequency band.

[0118] In this embodiment, the target frequency band is determined based on the application scenario of the microphone array, ensuring the matching degree between the target frequency band and the application scenario, avoiding interference from invalid frequency bands to the detection, and then the microphone array is subsequently tested for consistency based on the spectrum of the target frequency band, ensuring the effectiveness of the detection.

[0119] In another implementation, the process of the server determining the target frequency band also includes the following: the server divides the audio signal across the entire frequency band to obtain the spectrum of multiple frequency bands; the server selects the frequency band with the largest sum of amplitudes or the frequency band with the largest energy value as the target frequency band. In this implementation, since the frequency band with the largest sum of amplitudes or the frequency band with the largest energy value can effectively represent the frequency response characteristics of the microphone's audio signal, this method of determining the target frequency band ensures its rationality. Therefore, when performing consistency detection on the microphone array based on the spectrum of the target frequency band, the effectiveness of the detection can be guaranteed.

[0120] In this embodiment of the application, since the frequency bands where the sum of the amplitudes of the various microphones may be different, the computer device determines the average of the sum of the amplitudes of the multiple microphones in each frequency band, and takes the frequency band with the largest average as the target frequency band. Similarly, the computer device determines the second average of the energy values ​​of the multiple microphones in each frequency band, and takes the frequency band with the largest average as the target frequency band.

[0121] 303. The server divides the spectrum of the target frequency band into multiple sub-spectrums, with each sub-spectrum corresponding to a sub-frequency band.

[0122] In this embodiment, the number of sub-spectrums can be set and changed as needed, and no specific limitation is made in this embodiment. For example, the number of sub-spectrums can be 10 or 20, etc. The signal lengths of the multiple sub-spectrums are the same, that is, the frequency band length of each sub-band is the same. The resolution of each sub-spectrum can be set and changed as needed. The resolution is determined based on the number of frequency points in the sub-spectrum. The more frequency points, the higher the resolution, and the higher the accuracy of the sub-spectrum.

[0123] 304. For each of the multiple microphones other than the first microphone, the server determines the energy values ​​of each of the multiple sub-spectrums of the first microphone and the energy values ​​of each of the multiple sub-spectrums of the second microphone.

[0124] In this embodiment, the horizontal axis of the sub-spectrum represents frequency, and the vertical axis represents amplitude. For any sub-spectrum, the server uses the integral of the square of the amplitude in the sub-spectrum as the energy value of that sub-spectrum.

[0125] In this embodiment, since the first microphone is one of multiple microphones, it is subsequently used as a reference standard for consistency checks with each second microphone, thus improving the efficiency and convenience of obtaining the reference standard. In this embodiment, the process by which the server determines the first microphone includes the following steps.

[0126] The server determines the center position based on the positions of each microphone in the microphone array; the server designates the microphone at the center position as the first microphone. For example, if the microphone array includes five microphones arranged in a straight line, the server designates the third microphone at the center position as the first microphone. In this embodiment, by designating the microphone at the center position as the first microphone, the positional differences between the multiple second microphones and the first microphone are reduced because the distance between the microphone at the center position and the other microphones is relatively balanced.

[0127] It should be noted that in this embodiment, there is no microphone at the center of the multiple microphones. Therefore, the microphone closest to the center or any one of the multiple microphones can be selected as the first microphone. For example, if the microphone array includes four microphones arranged in a straight line, the server can select the second or third microphone closest to the center as the first microphone. Similarly, if the microphone array includes multiple microphones arranged in a circle, the server can select any one of the multiple microphones as the first microphone.

[0128] 305. For two sub-spectrums corresponding to the same sub-frequency band in the first microphone and the second microphone, the server determines the energy difference between the energy values ​​of the two sub-spectrums.

[0129] In this embodiment, the energy value of the sub-spectrum can effectively represent the characteristics of the sub-spectrum, thereby determining the energy difference between the energy values ​​of the two sub-spectrums corresponding to the same sub-frequency band in the two microphones. This difference can effectively represent the difference between the two sub-spectrums.

[0130] 306. The server uses the number of sub-frequency bands whose absolute value of the energy difference between multiple sub-frequency bands exceeds the first threshold as the difference degree.

[0131] In this embodiment, the first threshold can be set and changed as needed, such as 3dB. In this embodiment, the sub-frequency bands whose absolute value of the energy difference exceeds the first threshold are called abnormal sub-frequency bands, and the sub-frequency bands whose absolute value of the energy difference exceeds 3dB are abnormal sub-frequency bands.

[0132] It should be noted that due to differences in position or noise interference, the audio signals collected by the two microphones may have some unavoidable errors. However, in this embodiment, the number of sub-frequency bands whose absolute values ​​of the energy differences corresponding to multiple sub-frequency bands exceed a first threshold is used as the degree of difference, which allows for the existence of errors and thus ensures the rationality of determining the degree of difference. Furthermore, the degree of difference determined based on the differences of multiple sub-frequency bands improves the accuracy of determining the degree of difference and thus ensures the accuracy of the determined degree of difference.

[0133] 307. The server determines the consistency detection result between the second microphone and the first microphone based on the difference degree between multiple sub-spectrums of the second microphone and multiple sub-spectrums of the first microphone. The difference degree represents the difference between multiple sub-spectrums of the second microphone and multiple sub-spectrums of the first microphone.

[0134] It should be noted that due to differences in position or noise interference, the audio signals collected by the two microphones will inevitably produce some errors, therefore, the existence of these errors must be allowed. Accordingly, in this embodiment, the server determines that the consistency detection result between the second microphone and the first microphone is consistent if the difference does not exceed a second threshold. If the difference exceeds the second threshold, the server determines that the consistency detection result between the second microphone and the first microphone is inconsistent.

[0135] In one implementation of this application, the second threshold is positively correlated with the number of sub-spectrums; that is, the more sub-spectrums there are, the larger the second threshold. For example, if the number of sub-spectrums is 10, the second threshold is 3; if the number of sub-spectrums is 20, the second threshold is 6. This ensures that the second threshold matches the number of sub-spectrums, guaranteeing its reasonableness. In another implementation of this application, the second threshold is negatively correlated with the accuracy requirement of the microphone array consistency; that is, the higher the accuracy requirement, the smaller the second threshold. This approach, based on the accuracy requirements of the microphone array, improves the flexibility in determining the second threshold.

[0136] In this embodiment of the application, by determining the consistency detection result between the second microphone and the first microphone as consistent when the difference does not exceed the second threshold, the existence of error is allowed, thereby ensuring the rationality of the determined consistency detection result.

[0137] 308. If the server determines that the microphone array is consistent when the consistency detection results between each second microphone and the first microphone are consistent.

[0138] In this embodiment, after detecting whether the microphone array conforms to the consistency criteria in steps 301-308, the detection results can be used to determine whether the microphone array can normally acquire audio signals and whether the error between each microphone meets the requirements. In this embodiment, if the microphone array conforms to the consistency criteria, it can be determined that the microphone array can normally acquire audio signals and that the error between each microphone meets the requirements. Furthermore, in this embodiment, for a microphone array that conforms to the consistency criteria, it can be further determined whether the position of each microphone in the microphone array meets the design requirements to determine whether the microphone array meets the usage requirements.

[0139] In this embodiment of the application, the server determines whether the position of each microphone meets the requirements, and then determines whether the microphone array meets the usage requirements by means of the following method: the server locates the target playback device based on the audio signals of multiple microphones to obtain the estimated direction of the target playback device relative to the microphone array; if the actual direction of the target playback device relative to the microphone array matches the estimated direction, the server determines that the microphone array meets the usage requirements.

[0140] During the aforementioned audio signal acquisition process, the server determines the relative position of the target playback device and the microphone array through far-field sound propagation. The spatial position of the target acquisition device relative to the microphone array can be determined by establishing a corresponding coordinate system. In this embodiment, the server uses the center position of the microphone array as the origin, and the horizontal direction from left to right is the direction from 0 to 180 degrees. Therefore, the true direction of the target playback device relative to the microphone array is the 90-degree direction. The server uses a sound source localization algorithm to process the audio signals from multiple microphones to obtain the estimated direction of the target playback device relative to the microphone array. The sound wave localization algorithm includes at least one of beamforming algorithms, time-of-arrival difference algorithms, and acoustic holography algorithms.

[0141] In this embodiment, matching the actual direction with the estimated direction means that the angle difference between the actual direction and the estimated direction is within a preset range. If the actual direction matches the estimated direction, it indicates that the positions of each microphone in the microphone array are basically consistent with the actual position design, i.e., they meet the design requirements, and thus it can be determined that the microphone array meets the usage requirements. If the actual direction does not match the estimated direction, i.e., the angle difference between the estimated direction and the actual direction is large and exceeds the preset range, it indicates that the positions of each microphone in the microphone array do not all meet the design requirements, and there is a relatively obvious manufacturing error, and thus it can be determined that the microphone array does not meet the usage requirements.

[0142] In this embodiment, the microphones in the microphone array are each labeled with a different serial number. Accordingly, if the consistency detection result between at least one second microphone and the first microphone is inconsistent, the server outputs the serial number of that at least one second microphone. This output of the second microphone's serial number facilitates maintenance personnel in repairing the inconsistent second microphone.

[0143] In this embodiment of the application, the server also outputs the frequency band information of the sub-frequency bands whose absolute values ​​of the energy differences corresponding to the multiple sub-frequency bands of each second microphone with an output sequence number exceed the first threshold, thereby facilitating maintenance personnel to repair the second microphone based on the frequency band information.

[0144] In this embodiment, since the first microphone is one of the microphones in a microphone array, it may be a microphone that does not conform to the standard. Therefore, the sequence number of the at least one second microphone is only output after it is determined that the first microphone conforms to the standard. Accordingly, in this embodiment, the server outputs the sequence number of the at least one second microphone when the number of the at least one second microphone does not exceed a third threshold.

[0145] In the embodiments of this application, if the number of the at least one second microphone does not exceed a third threshold, it indicates that the first microphone used as a reference standard has a high probability of being a microphone that conforms to the consistency, and thus the accuracy of the at least one second microphone that does not conform to the consistency determined based on the first microphone is high.

[0146] In this embodiment, the third threshold is positively correlated with the number of microphones in the microphone array; that is, the more microphones there are, the larger the third threshold. For example, if there are 10 microphones, the third threshold can be 4; if there are 20 microphones, the third threshold can be 7. No specific limitation is made here.

[0147] In this embodiment, if the first microphone is inconsistent, it is necessary to redetermine the first microphone to re-perform consistency detection on the microphone array. Accordingly, if the number of at least one second microphone exceeds a third threshold, the server redetermines the first microphone from among the multiple second microphones and performs consistency detection on the microphone array based on multiple sub-spectrums of the redetermined first microphone.

[0148] It should be noted that if the number of at least one second microphone is too large, it means that there are too many second microphones that are inconsistent with the first microphone. In this case, the first microphone used as a reference standard is likely to be an inconsistent microphone. That is, the accuracy of determining that the first microphone is inconsistent is high. Then, the consistency detection of the microphone array is re-performed based on the re-determined first microphone, which ensures the accuracy of the detection.

[0149] In this embodiment, the server can determine the microphone closest to the center position among multiple second microphones as the new first microphone, or determine any one of the second microphones as the new first microphone; no specific limitation is made here. In this embodiment, after the server redetermines the first microphone, it also needs to output the sequence number of at least one second microphone based on the redetermined first microphone. The at least one second microphone refers to a microphone whose consistency detection result with the redetermined first microphone is inconsistent.

[0150] In this embodiment, consistency detection of the microphone array is performed based on multiple sub-spectrums of the first microphone in the microphone array, reducing the detection requirements and enabling rapid detection, thus improving detection efficiency and accuracy. See also Figure 4 , Figure 4 This is a flowchart illustrating a microphone array consistency detection method provided in an embodiment of this application. In this embodiment, a server acquires audio signals through a microphone array. The acquired audio signals are then subjected to an FFT transform to obtain frequency domain audio signals. The spectrum of the target frequency band in the audio signal is then divided into multiple sub-spectrums, and the energy values ​​of these sub-spectrums are determined. A difference degree is then obtained based on a first threshold and the difference between the energy values ​​of the multiple sub-spectrums of two microphones. This difference degree is then used to determine whether the two microphones are consistent. Next, it is determined whether each second microphone is consistent with the first microphone. If at least one second microphone is inconsistent with the first microphone, the microphone array is determined to be inconsistent, i.e., unqualified, and the sequence number of the at least one second microphone is output, i.e., the sequence number of the inconsistent microphone is output. If each second microphone is consistent with the first microphone, a sound source localization algorithm is used to determine whether the microphone array meets the position error requirements. If it does, the microphone array is determined to be qualified, i.e., meets the usage requirements; otherwise, the microphone array is determined to be unqualified, i.e., does not meet the usage requirements.

[0151] In this embodiment, by dividing the spectrum of the target frequency band in the audio signal of each microphone into multiple sub-spectrums, since each sub-spectrum can represent a detailed feature of the audio signal, the consistency detection result between the two microphones can be determined based on the difference between the multiple sub-spectrums of each microphone, which can improve the detection accuracy. Furthermore, using the first microphone among the multiple microphones as a reference standard, the consistency between the first microphone and the multiple second microphones is detected separately. Thus, if any second microphone is found to be inconsistent with the first microphone, it indicates that there is an inconsistent microphone in the microphone array, thereby determining that the microphone array is inconsistent, which improves the accuracy of consistency detection of the microphone array.

[0152] This application also provides a microphone array consistency detection device, see [link to relevant documentation]. Figure 5 The device includes:

[0153] The acquisition module 501 is used to acquire sound through multiple microphones in a microphone array to obtain audio signals from multiple microphones.

[0154] The first determining module 502 is used to determine the spectrum of the target frequency band in the audio signal of each microphone.

[0155] The partitioning module 503 is used to partition the spectrum of the target frequency band to obtain multiple sub-spectrums, with each sub-spectrum corresponding to a sub-frequency band.

[0156] The second determining module 504 is used to determine the consistency detection result between the second microphone and the first microphone for each second microphone other than the first microphone among the multiple microphones, based on the difference degree between the multiple sub-spectrums of the second microphone and the multiple sub-spectrums of the first microphone, where the difference degree represents the difference between the multiple sub-spectrums of the second microphone and the multiple sub-spectrums of the first microphone.

[0157] The third determining module 505 is used to determine that the microphone array is consistent when the consistency detection results between each second microphone and the first microphone are consistent.

[0158] In some embodiments, the apparatus further includes:

[0159] The fourth determining module is used to determine the energy values ​​of each of the multiple sub-spectrums of the first microphone and to determine the energy values ​​of each of the multiple sub-spectrums of the second microphone.

[0160] The fifth determining module is used to determine the energy difference between the energy values ​​of two sub-spectrums corresponding to the same sub-frequency band in the first microphone and the second microphone.

[0161] The sixth determining module is used to determine the number of sub-frequency bands whose absolute value of the energy difference corresponding to multiple sub-frequency bands exceeds the first threshold as the difference degree.

[0162] In some embodiments, the second determining module 504 is configured to:

[0163] If the difference does not exceed the second threshold, the consistency detection result between the second microphone and the first microphone is determined to be consistent.

[0164] In some embodiments, the acquisition module 501 is used for:

[0165] Play Gaussian white noise in the target scene using the target playback device;

[0166] Sound is captured in the target scene using a microphone array.

[0167] In some embodiments, the apparatus further includes:

[0168] The seventh determination module is used to determine the reference distance based on the array aperture of the microphone array and the minimum wavelength of the Gaussian white noise;

[0169] The eighth determining module is used to determine the horizontal distance based on the reference distance, where the horizontal distance is greater than or equal to the reference distance;

[0170] The ninth determining module is used to determine the second position based on the first position and horizontal distance of the target playback device, and the microphone array is used to collect sound at the second position.

[0171] In some embodiments, after determining that the microphone array conforms to the agreement, the device further includes:

[0172] The positioning module is used to locate the target playback device based on the audio signals from multiple microphones, so as to obtain the estimated orientation of the target playback device relative to the microphone array.

[0173] The tenth determination module is used to determine whether the microphone array meets the usage requirements when the actual direction of the target playback device relative to the microphone array matches the estimated direction.

[0174] In some embodiments, the apparatus further includes:

[0175] The eleventh determining module is used to determine the center position based on the positions of each microphone in the microphone array;

[0176] The twelfth determining module is used to designate the microphone at the center position as the first microphone.

[0177] In some embodiments, the microphones in the microphone array are each labeled with a different serial number, and the device further includes:

[0178] The output module is used to output the serial number of at least one second microphone when the consistency detection result between at least one second microphone and the first microphone is inconsistent.

[0179] In some embodiments, the output module is further configured to:

[0180] If the number of at least one second microphone does not exceed a third threshold, output the sequence number of at least one second microphone.

[0181] In some embodiments, the apparatus further includes:

[0182] The thirteenth determination module is used to redetermine the first microphone from multiple second microphones when the number of at least one second microphone exceeds a third threshold, and to perform consistency detection on the microphone array based on multiple sub-spectrums of the redetermined first microphone.

[0183] In some embodiments, the first determining module 502 is configured to:

[0184] In the case of microphone arrays used for speech detection, the frequency band containing the natural speech frequency in the audio signal is taken as the target frequency band;

[0185] In scenarios where microphone arrays are used for abnormal event detection, the frequency bands of the audio signal are all taken as the target frequency bands.

[0186] In this embodiment, the spectrum of the target frequency band in the audio signal of each microphone is divided into multiple sub-spectrums. Since each sub-spectrum can represent a detailed feature of the audio signal, the consistency detection result between the two microphones can be determined based on the difference between the multiple sub-spectrums of each microphone, which can improve the detection accuracy. Furthermore, since the two microphones of a consistent microphone array should be consistent, the consistency between the first microphone and the multiple second microphones is detected separately using the first microphone as a reference standard. If the consistency between each second microphone and the first microphone is consistent, it can be said that the microphone array is consistent, thus improving the accuracy of consistency detection of the microphone array.

[0187] It should be noted that the microphone array consistency detection device provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the control device can be divided into different functional modules to complete all or part of the functions described above. In addition, the microphone array consistency detection device and the microphone array consistency detection method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0188] In some embodiments, the computer device is provided as a control device. Figure 6 A structural block diagram of a control device 600 provided in an exemplary embodiment of this application is shown. The control device 600 can be a portable mobile control device, such as a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. The control device 600 may also be referred to as a user device, portable control device, laptop control device, desktop control device, or other names.

[0189] Typically, the control device 600 includes a processor 601 and a memory 602.

[0190] Processor 601 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 601 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 601 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 601 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 601 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0191] The memory 602 may include one or more computer-readable storage media, which may be non-transitory. The memory 602 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 602 are used to store at least one program code, which is executed by the processor 601 to implement the microphone array consistency detection method provided in the method embodiments of this application.

[0192] In some embodiments, the control device 600 may optionally include a peripheral device interface 603 and at least one peripheral device. The processor 601, memory 602, and peripheral device interface 603 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 603 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 604, a display screen 605, a camera assembly 606, an audio circuit 607, and a power supply 608.

[0193] Peripheral interface 603 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 601 and memory 602. In some embodiments, processor 601, memory 602 and peripheral interface 603 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 601, memory 602 and peripheral interface 603 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0194] The radio frequency (RF) circuit 604 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 604 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 604 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 604 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 604 can communicate with other control devices via at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 604 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0195] Display screen 605 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 605 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 601 for processing. In this case, display screen 605 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 605, disposed on the front panel of control device 600; in other embodiments, there may be at least two display screens, disposed on different surfaces of control device 600 or in a folded design; in still other embodiments, display screen 605 may be a flexible display screen, disposed on a curved or folded surface of control device 600. Furthermore, display screen 605 may be configured as a non-rectangular irregular shape, i.e., a non-rectangular screen. Display screen 605 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0196] The camera assembly 606 is used to acquire images or videos. Optionally, the camera assembly 606 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the control device, and the rear-facing camera is located on the back of the control device. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 606 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0197] The audio circuit 607 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting them into electrical signals that are input to the processor 601 for processing, or to the radio frequency circuit 604 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location in the control device 600. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 601 or the radio frequency circuit 604 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 607 may also include a headphone jack.

[0198] Power supply 608 is used to supply power to the various components in control device 600. Power supply 608 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 608 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, while a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0199] In some embodiments, the control device 600 further includes one or more sensors 609. The one or more sensors 609 include, but are not limited to, an acceleration sensor 610, a gyroscope sensor 611, a pressure sensor 612, an optical sensor 613, and a proximity sensor 614.

[0200] Accelerometer 610 can detect the magnitude of acceleration along the three axes of a coordinate system established by control device 600. For example, accelerometer 610 can be used to detect the components of gravitational acceleration along the three axes. Processor 601 can control display screen 605 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 610. Accelerometer 610 can also be used for games or for acquiring user motion data.

[0201] The gyroscope sensor 611 can detect the orientation and rotation angle of the control device 600. The gyroscope sensor 611, in conjunction with the accelerometer sensor 610, can collect 3D motion data from the user on the control device 600. Based on the data collected by the gyroscope sensor 611, the processor 601 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0202] The pressure sensor 612 can be disposed on the side bezel of the control device 600 and / or the lower layer of the display screen 605. When the pressure sensor 612 is disposed on the side bezel of the control device 600, it can detect the user's grip signal on the control device 600, and the processor 601 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 612. When the pressure sensor 612 is disposed on the lower layer of the display screen 605, the processor 601 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 605. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0203] An optical sensor 613 is used to collect ambient light intensity. In one embodiment, the processor 601 can control the display brightness of the display screen 605 based on the ambient light intensity collected by the optical sensor 613. Specifically, when the ambient light intensity is high, the display brightness of the display screen 605 is increased; when the ambient light intensity is low, the display brightness of the display screen 605 is decreased. In another embodiment, the processor 601 can also dynamically adjust the shooting parameters of the camera assembly 606 based on the ambient light intensity collected by the optical sensor 613.

[0204] The proximity sensor 614, also known as a distance sensor, is typically mounted on the front panel of the control device 600. The proximity sensor 614 is used to detect the distance between the user and the front of the control device 600. In one embodiment, when the proximity sensor 614 detects that the distance between the user and the front of the control device 600 is gradually decreasing, the processor 601 controls the display screen 605 to switch from a screen-on state to a screen-off state; when the proximity sensor 614 detects that the distance between the user and the front of the control device 600 is gradually increasing, the processor 601 controls the display screen 605 to switch from a screen-off state to a screen-on state.

[0205] Those skilled in the art will understand that Figure 6 The structure shown does not constitute a limitation on the control device 600, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0206] In some embodiments, the computer device is provided as a server. Figure 7This is a block diagram of a server provided in an embodiment of this application. The server 700 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 701 and one or more memories 702. The memories 702 are used to store executable program code, and the processors 701 are configured to execute the executable program code to implement the microphone array consistency detection method provided in the various method embodiments described above. Of course, the server may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server may also include other components for implementing device functions, which will not be elaborated here.

[0207] In an exemplary embodiment, a storage medium including program code is also provided, such as a memory 702 including program code, which can be executed by the processor 701 of the server 700 to complete the microphone array consistency detection method described above. Optionally, the storage medium can be a non-transitory computer-readable storage medium, such as ROM (Read-Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk, and optical data storage device.

[0208] This application also provides a computer-readable storage medium storing at least one piece of program code, which is loaded and executed by a processor to implement the microphone array consistency detection method of any of the above implementations.

[0209] This application also provides a computer program product, which includes computer program code stored in a computer-readable storage medium. The processor of a computer device reads the computer program code from the computer-readable storage medium and executes the computer program code, causing the computer device to perform the microphone array consistency detection method of any of the above implementations.

[0210] In some embodiments, the computer program product involved in the present application can be deployed and executed on a computer device, or on multiple computer devices located in one location, or on multiple computer devices distributed in multiple locations and interconnected through a communication network. Multiple computer devices distributed in multiple locations and interconnected through a communication network can form a blockchain system.

[0211] The above are merely optional embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method of detecting consistency of a microphone array, the method comprising: The method comprises: playing Gaussian white noise by a target playing device in a target scene; collecting sound by a plurality of microphones in a microphone array in the target scene to obtain audio signals of the plurality of microphones; in a case where the microphone array is used in a voice detection scene, taking a frequency band in which natural voice frequency is located in the audio signals as the target frequency band; in a case where the microphone array is used in an abnormal event detection scene, taking each frequency band of the audio signals as the target frequency band; for each microphone, determining a spectrum of the target frequency band in the audio signal of the microphone; dividing the spectrum of the target frequency band to obtain a plurality of sub-spectra, one sub-spectrum corresponding to one sub-frequency band, the sub-spectrum representing a detailed feature of the audio signal, and the frequency band length of each sub-frequency band being the same; for each second microphone except a first microphone in the plurality of microphones, determining a consistency detection result between the second microphone and the first microphone based on a difference degree between the plurality of sub-spectra of the second microphone and the plurality of sub-spectra of the first microphone, the difference degree representing a difference between the plurality of sub-spectra of the second microphone and the plurality of sub-spectra of the first microphone; in a case where the consistency detection result between at least one second microphone and the first microphone is inconsistent, in a case where the number of the at least one second microphone exceeds a third threshold, determining a microphone closest to a center position in a plurality of second microphones as a new first microphone, and performing consistency detection on the microphone array based on the plurality of sub-spectra of the newly determined first microphone; in a case where the consistency detection result between each second microphone and the first microphone is consistent, determining that the microphone array is consistent; based on the audio signals of the plurality of microphones, positioning the target playing device to obtain an estimated direction of the target playing device relative to the microphone array; in a case where an angle difference between a real direction of the target playing device relative to the microphone array and the estimated direction is within a preset range, the real direction matches the estimated direction, and it is determined that the microphone array meets a use requirement.

2. The method of claim 1, wherein, The method further comprises: determining an energy value of each of the plurality of sub-spectra of the first microphone and determining an energy value of each of the plurality of sub-spectra of the second microphone; for two sub-spectra corresponding to a same sub-frequency band in the first microphone and the second microphone, determining an energy difference value between the energy values of the two sub-spectra; taking a number of sub-frequency bands corresponding to the energy difference values whose absolute values exceed a first threshold as the difference degree.

3. The method according to claim 1 or 2, characterized in that, The determining of the consistency detection result between the second microphone and the first microphone based on the difference degree between the plurality of sub-spectra of the second microphone and the plurality of sub-spectra of the first microphone comprises: in a case where the difference degree does not exceed a second threshold, determining that the consistency detection result between the second microphone and the first microphone is consistent.

4. The method of claim 1, wherein, The method further comprises: determine a reference distance based on an array aperture of the microphone array and a minimum wavelength of the Gaussian white noise; determine a horizontal distance based on the reference distance, the horizontal distance being greater than or equal to the reference distance; determine a second position based on a first position of the target playback device and the horizontal distance, the microphone array being used to collect sound at the second position.

5. The method of claim 1, wherein, The method further includes: determine a center position based on positions of the microphones in the microphone array; use a microphone at the center position as the first microphone.

6. The method of claim 1, wherein, The plurality of microphones in the microphone array are respectively labeled with different serial numbers, and the method further includes: in a case where a consistency detection result between at least one second microphone and the first microphone is inconsistent, output a serial number of the at least one second microphone.

7. The method of claim 6, wherein, The method further includes: in a case where a number of the at least one second microphone does not exceed a third threshold, output the serial number of the at least one second microphone.

8. A device for detecting uniformity of a microphone array, characterized by, The apparatus includes: a collection module configured to cause a target playback device to play Gaussian white noise in a target scene, and cause a plurality of microphones in a microphone array to collect sound in the target scene to obtain audio signals of the plurality of microphones; a first determination module configured to, for each microphone, determine a spectrum of a target frequency band in the audio signal of the microphone; a division module configured to, in a case where the microphone array is used in a voice detection scene, use a frequency band in which a natural voice frequency is located in the audio signal as the target frequency band, in a case where the microphone array is used in an abnormal event detection scene, use all frequency bands in the audio signal as the target frequency band, and divide the spectrum of the target frequency band to obtain a plurality of sub-spectra, one sub-spectrum corresponding to one sub-band, the sub-spectrum representing a detailed feature of the audio signal, and each sub-band having a same frequency band length; a second determination module configured to, for each second microphone other than a first microphone in the plurality of microphones, determine a consistency detection result between the second microphone and the first microphone based on a difference degree between a plurality of sub-spectra of the second microphone and a plurality of sub-spectra of the first microphone, the difference degree representing a difference between the plurality of sub-spectra of the second microphone and the plurality of sub-spectra of the first microphone; a thirteenth determination module configured to, in a case where the consistency detection result between at least one second microphone and the first microphone is inconsistent, in a case where a number of the at least one second microphone exceeds a third threshold, determine a microphone closest to a center position from a plurality of second microphones as a new first microphone, and perform consistency detection on the microphone array based on a plurality of sub-spectra of the newly determined first microphone; a third determination module configured to, in a case where the consistency detection result between each second microphone and the first microphone is consistent, determine that the microphone array is consistent. a positioning module, configured to position the target playback device based on audio signals of the plurality of microphones to obtain an estimated direction of the target playback device relative to the microphone array; a tenth determining module, configured to determine that the microphone array meets the use requirement in a case where an angle difference between an actual direction of the target playback device relative to the microphone array and the estimated direction is within a preset range, the actual direction being matched with the estimated direction.

9. A computer device, comprising: The computer device comprises one or more processors and one or more memories, and the one or more memories store at least one program code, the at least one program code is loaded and executed by the one or more processors to implement the microphone array consistency detection method in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores at least one program code, and the at least one program code is loaded and executed by the processor to implement the microphone array consistency detection method in any one of claims 1 to 7.

11. A computer program product, characterised in that, The computer program product comprises computer program code stored in a computer readable storage medium, and the processor of the computer device reads the computer program code from the computer readable storage medium, and the processor executes the computer program code, so that the computer device executes the microphone array consistency detection method in any one of claims 1 to 7.

Images