Speech enhancement system and method based on MFrSRRPCA algorithm

Abstract

The invention discloses a speech enhancement system and method based on a multi-subband short-time fractional Fourier spectrum random rearrangement robust principal component analysis MFrSRRPCA algorithm. The realization steps are: a time-frequency analysis module generates time-frequency information of noisy speech; the time-frequency analysis module generates time-frequency information of noisyspeech. The time-frequency subband division module divides the time-frequency amplitude spectrum of the noisy speech into a plurality of noisy subbands. Each time-frequency amplitude spectrum enhancement module randomly disrupts the sequence of each frame spectrum element in the corresponding noisy sub-band, and generates the corresponding enhancement sub-band by using a robust principal componentanalysis algorithm according to the noise intensity estimation value in the corresponding sub-band. The time-frequency subband recombination module composes all the enhancement subbands to enhance the time-frequency amplitude spectrum. The time-domain speech reconstruction module reconstructs the enhanced time-frequency amplitude spectrum into enhanced speech. The invention can improve the soundquality and intelligibility of the noisy speech, and can be used for the speech enhancement and noise reduction of the speech receiving system.

Description

technical field [0001] The invention belongs to the field of signal processing, and further relates to a multi-band short-time fractional Fourier spectrum random rearrangement based robust principal component analysis MFrSRRPCA (Multi-band Short-time-fractional- Speech enhancement system and method of Fourier-spectrogram-random-rearranged Robust Principal Component Analysis) algorithm. The invention can not only be used for speech enhancement and noise reduction in a speech receiving system, but also can be used as a preprocessing front end of a speech detection and recognition system to improve the performance of speech detection and recognition. Background technique [0002] Traditional speech enhancement is usually based on algorithms such as spectral subtraction and Wiener filter, and the enhanced speech obtained by spectral subtraction often introduces a lot of music noise, but the Wiener filter presupposes that the speech and noise obey the Gaussian distribution. There...

AI Technical Summary

Problems solved by technology

However, the system still has the disadvantage that, since the system only contains one time-frequency amplitude spectrum enhancement module, the speech enhancement parameters can only be set according to a single time-frequency amplitude spectrum, so the system eliminates energy in time-frequency When non-uniformly distributed colored noise in the magnitude spectrum, a large number of colored noise components will remain in the enhanced speech

However, the disadvantage of this method is that because this method only limits the size of the low-rank matrix to reduce the possibility of low-rank speech components being eliminated by mistake, it does not fundamentally solve the problem. Therefore, there are still Some low-rank speech is regarded as noise and filtered out, which affects the intelligibility of speech

Images