Multi-microphone Speech Enhancement Method Based on Tensor Decomposition

Abstract

The invention discloses a multi-microphone voice enhancement method based on tensor decomposition, which comprises the following steps: a 3D tensor is used for expressing multi-channel voice signals observed by a plurality of microphones, and the tensor is projected to a series of orthogonal basis; a minimization statistical risk criterion is adopted to collect a noise section in real time; noisecovariance is tracked, and an optimal threshold is calculated according to the size of the tensor block. According to the method, the received multi-channel data are represented as a three-order tensor, so that original spatial information and time information are reserved, background noise and weak directional noise can be removed more obviously, and voice distortion can be reduced as much as possible.

Description

technical field [0001] The invention relates to the field of voice noise reduction, in particular to a multi-microphone voice enhancement method based on tensor decomposition. Background technique [0002] In the field of speech enhancement, although the classic single-channel algorithm can remove more background noise, it is easy to cause speech distortion, and even bring "music" noise, resulting in speech quality damage. By using a microphone array and using a beamforming algorithm, better suppression of directional interference can be achieved. [0003] Traditional speech enhancement algorithms based on microphone arrays can be divided into time-domain noise reduction algorithms and frequency-domain noise reduction algorithms. The time-domain algorithm usually stitches the speech frames output by each microphone, and performs optimal linear filtering on this extended frame. The frequency domain algorithm performs Fourier transform on each microphone frame, extracts the ...

AI Technical Summary

Problems solved by technology

However, vector-based representation methods cannot make full use of the space, time, and frequency information carried in multi-channel data, so there is room for improvement

[0004] In addition, in many cases the noise received by the microphone array is not completely directional interference, which makes the beamforming technology based on the principle of spatial filtering extremely vulnerable to performance loss

For background noise with no obvious directionality or even no directionality, the spatial filtering effect of the beamforming algorithm is not good, which will bring more noise residues

Images