Speech enhancement combining statistical models and NMF with update of speech and noise bases

Kisoo Kwon, Jong Won Shin, Sukanya Sonowal, In Kyu Choi, Nam Soo KimICASSP 2014 · OpenReview

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.
BibTeX
@inproceedings{kwon2014speech,
  author = {Kisoo Kwon and Jong Won Shin and Sukanya Sonowal and In Kyu Choi and Nam Soo Kim},
  title = {{Speech enhancement combining statistical models and NMF with update of speech and noise bases}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2014},
  url = {https://openreview.net/forum?id=6d0O34CDta},
}

Loading related content...

Figure