Télécom Paris

Markov-Switching GARCH Model and Application to Speech Enhancement in Subbands
  • Ari Abramson, (Department of Electrical Engineering, Technion)
  • Israel Cohen, (Department of Electrical Engineering, Technion)
  • Sound enhancement and sound separation
  • Noise reduction techniques
Get the paper in PDF format
Acrobat Reader (version 5 minimum) is necessary to read this document.

In this paper, we introduce a Markov-switching generalized autoregressive conditional heteroscedasticity (GARCH) model in the short-time Fourier transform (STFT) domain. A GARCH model is utilized with Markov switching regimes, where the parameters are assumed to be frequency variant. The model parameters are evaluated in each frequency subband and a special state (regime) is defined for the case where speech coefficients are absent or bellow a threshold level. The problem of speech enhancement under speech presence uncertainty is addressed and it is shown a soft voice activity detector may be inherently incorporated within the algorithm. Experimental results demonstrate the potential of our proposed model to improve noise reduction while retaining weak components of the speech signal.

©2006 Télécom Paris/TSI
Edition : Télécom Paris -- 2006