A non-negative approach to semi-supervised separation of speech from noise with the use of temporal dynamics - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

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

Résumé

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.
Fichier principal
Vignette du fichier
mysore-icassp2011.pdf (723.31 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01084337 , version 1 (19-11-2014)

Identifiants

Citer

Gautham Jean 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⟩
22 Consultations
137 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More