A non-negative approach to semi-supervised separation of speech from noise with the use of temporal dynamics

Abstract

We present a semi-supervised source separation methodology to denoise speech by modeling speech as one source and noise as the other source. We model speech using the recently proposed non-negative hidden Markov model, which uses multiple non-negative dictionaries and a Markov chain to jointly model spectral structure and temporal dynamics of speech. We perform separation of the speech and noise using the recently proposed non-negative factorial hidden Markov model. Although the speech model is learned from training data, the noise model is learned during the separation process and requires no training data. We show that the proposed method achieves superior results to using non-negative spectrogram factorization, which ignores the non-stationarity and temporal dynamics of speech.

DOI: 10.1109/ICASSP.2011.5946317

Extracted Key Phrases

7 Figures and Tables

010202011201220132014201520162017
Citations per Year

70 Citations

Semantic Scholar estimates that this publication has 70 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Mysore2011ANA, title={A non-negative approach to semi-supervised separation of speech from noise with the use of temporal dynamics}, author={Gautham J. Mysore and Paris Smaragdis}, journal={2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, year={2011}, pages={17-20} }