Skip to Main content Skip to Navigation
Conference papers

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 pro posed 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 re quires 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.
Complete list of metadata

Cited literature [8 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01084337
Contributor : Ist Inria Saclay <>
Submitted on : Wednesday, November 19, 2014 - 9:19:34 AM
Last modification on : Thursday, August 1, 2019 - 2:12:06 PM
Long-term archiving on: : Friday, April 14, 2017 - 8:29:56 PM

File

mysore-icassp2011.pdf
Files produced by the author(s)

Identifiers

Citation

Gautham Mysore, Paris Smaragdis. A non-negative approach to semi-supervised separation of speech from noise with the use of temporal dynamics. IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP 2011, May 2011, Prague, Czech Republic. pp.17-20, ⟨10.1109/ICASSP.2011.5946317⟩. ⟨hal-01084337⟩

Share

Metrics

Record views

63

Files downloads

326