NMF-Based Speech Enhancement Using Bases Update

• Published in: IEEE signal processing letters 2015-04, Vol.22 (4), p.450-454
• Main Authors: Kwon, Kisoo, Shin, Jong Won, Kim, Nam Soo
• Format: Article
• Language: English
• Subjects: Computational modeling; Factorization; Gain; Mathematical models; Noise; Non-negative matrix factorization; on-line bases update; On-line systems; Signal processing; Speech; Speech enhancement; Statistical analysis; statistical model-based enhancement; Training; Vectors
• ISSN: 1070-9908; 1558-2361
• DOI: 10.1109/LSP.2014.2362556

This letter presents a speech enhancement technique combining statistical models and non-negative matrix factorization (NMF) with on-line update of speech and noise bases. The statistical model-based enhancement methods have been known to be less effective to non-stationary noises while the template-based enhancement techniques can deal with them quite well. However, the template-based enhancement techniques usually rely on a priori information. To overcome the shortcomings of both approaches, we propose a novel speech enhancement method that combines the statistical model-based enhancement scheme with the NMF-based gain function. For a better performance in time-varying noise environments, both the speech and noise bases of NMF are adapted simultaneously with the help of the estimated speech presence probability. Experimental results showed that the proposed method outperformed not only the statistical model-based and NMF approaches, but also their combination in various noise environments.