Voice acquiring method and device adopting plurality of microphones

Abstract

The invention provides a voice acquiring method and a voice acquiring device adopting a plurality of microphones. The method comprises the following steps: carrying out voice acquiring by adopting theplurality of microphones, wherein the microphones correspond to different voice acquiring channels, and thus voice signals of each voice acquiring channel are obtained; carrying out analog-digital conversion on the voice signals, thus obtaining voice digital signals; carrying out framing processing on PCM binary data of the voice digital signals, thus obtaining short-time stable audio signals corresponding to each frame of PCM binary data; carrying out voice activity detection on the short-time stable audio signals in sequence according to the frames, and determining the frames correspondingto the short-time stable audio signals as voice frames or non-voice frames; carrying out voice quality detection on fragment audio files corresponding to the voice frames by adopting the preset framenumber as the step size, and saving the fragment audio files with the qualified quality; and splicing the saved fragment audio files with the qualified quality for synthesizing the complete audio file.

Description

technical field [0001] The invention relates to the technical field of voice signal processing, in particular to a multi-microphone voice collection method and device. Background technique [0002] The training of the voiceprint recognition system model needs to collect speaker information from a large number of different speaker voices (from different channels and different background noises), so as to improve the noise immunity of the system. Due to the difference of background environment noise and transmission channel, the characteristic distribution of training speech and test speech is not the same, which will seriously affect the recognition effect of the speaker recognition system. Therefore, the acquisition process of human voice should cover as many channels and background noise as possible. In the "Voice Multi-channel Simulation and Acquisition Method" of HKUST Xunfei, multi-channel synchronous acquisition and simulation of various voice channels are used to quic...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a multi-microphone voice collection method and device, which solves the lack of a process for quantitatively evaluating voice quality in the multi-microphone collection method in the prior art, resulting in the need to clean the stored audio data again and increase additional work Quantitative technical issues

Images