Paper Info
Title
Speech enhancement combining statistical models and NMF with update of speech and noise bases
Abstract
Speech enhancement based on statistical models has shown good performance, but the performance degrades when environment noise is highly non-stationary due to the stationary assumption. On the contrary, the template-based enhancement methods are more robust to non-stationary noise, but these are heavily dependent on a priori information present in training data. In order to get over both of the shortcomings, we propose a novel speech enhancement method which combines the statistical model-based enhancement scheme with the template-based enhancement. To reduce a dependency on a priori information, the speech and noise bases are updated simultaneously using the estimated speech presence probability, which is obtained from statistical model-based enhancement. Experimental results showed that the proposed method outperformed not only the statistical model-based and non-negative matrix factorization (NMF) approaches, but also their combination implemented with existing bases update rule in various kinds of noise.
Year
DOI
Venue
2014
10.1109/ICASSP.2014.6854968
ICASSP
Keywords
Field
DocType
on-line update of bases,nmf,noise base,speech presence probability,nonnegative matrix factorization,speech base,matrix decomposition,non-negative matrix factorization,template based enhancement,speech enhancement,statistical model-based enhancement,statistical model based enhancement,probability
Training set,Speech enhancement,Pattern recognition,Computer science,A priori and a posteriori,Matrix decomposition,Speech recognition,Statistical model,Artificial intelligence,Non-negative matrix factorization
Conference
ISSN
Citations 
PageRank 
1520-6149
2
0.37
References 
Authors
7
5
Name
Order
Citations
PageRank
Kisoo Kwon1353.35
Jong Won Shin221521.85
Sukanya Sonowat320.37
In Kyu Choi422.06
Nam Soo Kim534.11