Nonstationary-state hidden Markov model representation of speech signals for speech enhancement

Authors:
Hossein Sameti;Li Deng
Affiliations:
Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Ont., Canada;Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Ont., Canada N2L 3G1 and Microsoft Research, One Microsoft Way, Redmond, WA
Venue:
Signal Processing
Year:
2002

Citing 3
Cited 1

A generalized hidden Markov model with state-conditioned trend functions of time for the speech signal

Signal Processing
Model-based approaches to speech enhancement: stationary-state and nonstationary-state hmms

Model-based approaches to speech enhancement: stationary-state and nonstationary-state hmms
Speech recognition and enhancement by a nonstationary AR HMM with gain adaptation under unknown noise

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01

The study of a nonstationary maximum entropy Markov model and its application on the pos-tagging task

ACM Transactions on Asian Language Information Processing (TALIP)

Quantified Score

Hi-index	0.08

Visualization

Abstract

A novel formulation of the nonstationary-state hidden Markov model (NS-HMM), employed as the speech model and serving as the theoretical basis for the construction of a speech enhancement system, is presented in this paper. The NS-HMM is used as a compact, parametric model, generalized from the stationary-state HMM, for describing clean speech statistics in the construction of the minimum mean-square-error (MMSE) speech enhancement system. The feature selection problem associated with the use of the NS-HMM in designing the speech enhancement system is addressed. The MMSE formulation is derived where the NS-HMM is used as the clean speech model and Gaussian-mixture, stationary-state HMM as the additive noise model. Speech enhancement experiments are conducted, demonstrating superiority of the NS-HMM over the stationary-state HMM in the speech enhancement performance for low SNRs. Detailed diagnostic analysis on the speech enhancement system's operation shows that the superiority arises from the ability of the NS-HMM to fit the spectral trajectory of the signal embedded in noise more closely than the stationary-state HMM.