For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Online Convolutive Non-Negative Bases Learning for Speech Enhancement
Yinan LI Xiongwei ZHANG Meng SUN Yonggang HU Li LI
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2016/08/01
Online ISSN: 1745-1337
Type of Manuscript: LETTER
Category: Speech and Hearing
convolutive non-negative sparse coding, online learning, speech enhancement,
Full Text: PDF(165.4KB)
>>Buy this Article
An online version of convolutive non-negative sparse coding (CNSC) with the generalized Kullback-Leibler (K-L) divergence is proposed to adaptively learn spectral-temporal bases from speech streams. The proposed scheme processes training data piece-by-piece and incrementally updates learned bases with accumulated statistics to overcome the inefficiency of its offline counterpart in processing large scale or streaming data. Compared to conventional non-negative sparse coding, we utilize the convolutive model within bases, so that each basis is capable of describing a relatively long temporal span of signals, which helps to improve the representation power of the model. Moreover, by incorporating a voice activity detector (VAD), we propose an unsupervised enhancement algorithm that updates the noise dictionary adaptively from non-speech intervals. Meanwhile, for the speech intervals, one can adaptively learn the speech bases by keeping the noise ones fixed. Experimental results show that the proposed algorithm outperforms the competing algorithms substantially, especially when the background noise is highly non-stationary.