CN-119724213-B - Data acquisition method and device, electronic equipment and storage medium

CN119724213BCN 119724213 BCN119724213 BCN 119724213BCN-119724213-B

Abstract

The application discloses a data acquisition method, a data acquisition device, electronic equipment and a storage medium. The method comprises the steps of obtaining audio to be processed, which is collected through a microphone array and comprises multiple sentences of multi-channel audio, and obtaining phase difference characteristics among at least one group of appointed channel audio as target data, wherein each sentence of multi-channel audio comprises at least two channel audio with associated positions. According to the method, for each sentence of multi-channel audio, phase difference calculation is carried out on the audio of at least two microphone channels with position correlation, on one hand, phase information coverage with higher dimensionality can be generated, DOA features obtained after the phase difference are denser, and therefore accuracy of DOA coding results is improved, and on the other hand, data redundancy can be avoided due to the fact that the phase difference calculation is carried out on the audio of the microphone channels with the position correlation, and therefore efficiency of DOA coding is improved.

Inventors

LI RONGJIN
CHEN DONGPENG
ZHANG WEIBIN

Assignees

深圳市声扬科技有限公司

Dates

Publication Date: 20260508
Application Date: 20241202

Claims (8)

1. A method of data acquisition, the method comprising: acquiring audio to be processed acquired by a microphone array, wherein the audio to be processed comprises multiple sentences of multichannel audio; Carrying out Fourier transform on each sentence of multi-channel audio to obtain a real part parameter and an imaginary part parameter corresponding to each channel audio; determining the number of channel audios included in the designated channel audio; Acquiring a first phase difference and a second phase difference between at least one group of channel audios based on the corresponding real part parameter and imaginary part parameter, wherein the second phase difference is ninety-degree sinusoidal with the first phase difference; splicing the first phase difference and the second phase difference to obtain a phase difference characteristic as target data, wherein the target data is used for encoding the direction of arrival; the method comprises the steps of obtaining a first phase difference and a second phase difference between at least one group of channel audios based on corresponding real part parameters and imaginary part parameters when the number of the channel audios to be processed acquired by the microphone array is one group, carrying out phase difference on each channel audio of the two channel audios adjacent to the center channel audio and the corresponding imaginary part parameter to obtain two phase difference results to be processed, carrying out difference on the two phase difference results to obtain a target phase difference result, obtaining a cosine value of the target phase difference result as the first phase difference, and obtaining a sine value of the target phase difference result as the second phase difference; If the audio to be processed collected by the microphone array does not include the central channel audio collected by the central microphone of the microphone array, and the designated channel audio includes any three adjacent channel audios, the central channel audio of the designated channel audio is the middle channel audio of the three adjacent channel audios.
2. The method according to claim 1, wherein, in a case where the number of the specified channel tones is a set, and if the audio to be processed collected by the microphone array includes a center channel tone, the specified channel tone includes the center channel tone and any one of the other channel tones, the obtaining a first phase difference and a second phase difference between at least one set of the number of channel tones based on the corresponding real part parameter and imaginary part parameter includes: Carrying out phase difference on the audio of any one other channel and the audio of the center channel based on the real part parameter and the imaginary part parameter corresponding to the audio of any one other channel and the real part parameter and the imaginary part parameter corresponding to the audio of the center channel to obtain a phase difference result; acquiring a cosine value of the phase difference result as the first phase difference; And acquiring a sine value of the phase difference result as the second phase difference.
3. The method of claim 2, wherein if the audio to be processed collected by the microphone array does not include center channel audio, the designated channel audio includes any two adjacent channel audio.
4. The method according to claim 1, wherein, in a case where the number of the specified channel tones is a set, and if the microphone array includes two center channel tones, the specified channel tones include the two center channel tones and any two other channel tones adjacent in position, the acquiring the first phase difference and the second phase difference between at least one set of the number of channel tones based on the corresponding real part parameter and imaginary part parameter includes: Based on the real part parameter and the imaginary part parameter corresponding to each of the other adjacent channel audios at any two positions and the real part parameter and the imaginary part parameter corresponding to each of the two center channel audios, carrying out phase difference on each of the two adjacent channel audios and one center channel audio with a relatively short interval distance to obtain a first to-be-processed phase difference result and a second to-be-processed phase difference result; based on real part parameters and imaginary part parameters corresponding to the two center channel audios, carrying out phase difference on the two center channel audios to obtain a third to-be-processed phase difference result; the first to-be-processed phase difference result and the third to-be-processed phase difference result are subjected to difference to obtain a first reference phase difference result; the second to-be-processed phase difference result and the third to-be-processed phase difference result are subjected to difference to obtain a second reference phase difference result; performing difference on the first reference phase difference result and the second reference phase difference result to obtain a target phase difference result; Acquiring a cosine value of the target phase difference result as the first phase difference; and acquiring a sine value of the target phase difference result as the second phase difference.
5. The method of claim 4, wherein if the audio to be processed collected by the microphone array does not include center channel audio collected by a center microphone of the microphone array, the designated channel audio includes any four channel audio adjacent to each other, the method further comprising: and taking the middle two channel audios of the four adjacent channel audios as the center channel audio of the appointed channel audio.
6. A data acquisition device, the device comprising: The audio processing device comprises an audio processing module, a processing module and a processing module, wherein the audio processing module is used for processing audio acquired through a microphone array, and the audio processing module is used for processing audio acquired through the microphone array; The system comprises a data acquisition module, a data processing module, a phase difference feature acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for carrying out Fourier transform on each sentence of multi-channel audio to obtain a real part parameter and an imaginary part parameter corresponding to each channel audio, determining the number of channel audio included in appointed channel audio, acquiring a first phase difference and a second phase difference between at least one group of channel audio based on the corresponding real part parameter and the imaginary part parameter, wherein the second phase difference and the first phase difference are different by ninety degrees in sine, and splicing the first phase difference and the second phase difference to obtain a phase difference feature which is used as target data for carrying out direction of arrival coding; The data acquisition module is configured to, when the number of the specified channel audios is a set, perform phase difference on each of the two channel audios adjacent to each other to obtain two to-be-processed phase difference results, perform difference on the two to-be-processed phase difference results to obtain a target phase difference result, obtain a cosine value of the target phase difference result as the first phase difference, obtain a sine value of the target phase difference result as the second phase difference, and if the to-be-processed audio collected by the microphone array does not include the center channel audio collected by the microphone array and the specified channel audio includes the center channel audio collected by the microphone array, the specified channel audio includes the three to-be-processed audio adjacent to the center channel audio of the specified channel audio.
7. An electronic device comprising one or more processors and memory; one or more programs stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-5.
8. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program code, wherein the program code, when being executed by a processor, performs the method of any of claims 1-5.

Description

Data acquisition method and device, electronic equipment and storage medium Technical Field The present application relates to the field of data acquisition technologies, and in particular, to a data acquisition method, apparatus, electronic device, and storage medium. Background A multi-channel microphone array may estimate the direction of arrival (direction of arrival, DOA) of sound based on a neural network's target speech extraction algorithm (TARGET SPEECH extraction, TSE), thereby estimating the direction and distance of the sound source. In the working process of the multi-channel microphone array, DOA features need to be encoded, however, the DOA features obtained by the phase difference between channels at present are sparse, so that accurate DOA encoding results are difficult to obtain. Disclosure of Invention The application provides a data acquisition method, a data acquisition device, electronic equipment and a storage medium, so as to solve the problems. In a first aspect, an embodiment of the present application provides a data acquisition method, where the method includes acquiring audio to be processed acquired by a microphone array, where the audio to be processed includes multiple multi-channel audio, and for each multi-channel audio, acquiring a phase difference characteristic between at least one set of designated channel audio as target data, where the designated channel audio includes at least two channel audio associated with a position. In a second aspect, an embodiment of the present application provides a data acquisition apparatus, where the apparatus includes a to-be-processed audio acquisition module configured to acquire to-be-processed audio acquired by a microphone array, where the to-be-processed audio includes multiple multi-channel audio, and a data acquisition module configured to acquire, for each of the multiple-channel audio, a phase difference characteristic between at least one set of specified channel audio as target data, where the specified channel audio includes at least two channel audio associated in position. In a third aspect, an embodiment of the present application provides an electronic device, including one or more processors, a memory, and one or more applications, where the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to perform the data acquisition method provided in the first aspect. In a fourth aspect, an embodiment of the present application provides a computer readable storage medium having stored therein program code that is callable by a processor to perform the data acquisition method provided in the first aspect above. The method, the device, the electronic equipment and the storage medium for acquiring the data acquire the audio to be processed acquired through the microphone array, wherein the audio to be processed comprises multiple multi-channel audios, and for each multi-channel audio, the phase difference characteristic between at least one group of designated channel audios is acquired and used as target data, and the designated channel audios comprise at least two channel audios with associated positions. Therefore, for each sentence of multi-channel audio, the phase difference calculation is carried out by the audio of at least two microphone channels with the position correlation, on one hand, the phase information coverage with higher dimensionality can be generated, so that DOA characteristics obtained after the phase difference are denser, the accuracy of DOA coding results is improved, and on the other hand, the data redundancy can be avoided by adopting the microphone channel audio with the position correlation to carry out the phase difference calculation, and the DOA coding efficiency is improved. Drawings In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Fig. 1 shows a flowchart of a data acquisition method according to an embodiment of the present application. Fig. 2 is a diagram showing an example of the shape of a microphone array according to an embodiment of the present application. Fig. 3 shows a method flow chart of step S120 of fig. 1. Fig. 4 shows a structural example diagram of a DOA encoder provided by an embodiment of the present application. Fig. 5 is a flowchart of a data acquisition method according to another embodiment of the present application. Fig. 6 is a diagram showing an example of the positional arrangement between different channel audios in the case where the designated channel audio provided i