Iterative Speech Enhancement using a Non-Linear Dynamic State Model of Speech and its Parameters

Author

Windmann, Stefan ; Haeb-Umbach, Reinhold

Author_Institution

Dept. of Commun. Eng., Paderborn Univ.

Volume

1

fYear

2006

fDate

14-19 May 2006

Abstract

A marginalized particle filter is proposed for performing single channel speech enhancement with a non-linear dynamic state model. The system consists of a particle filter for tracking line spectral pair (LSP) parameters and a Kalman filter per particle for speech enhancement. The state model for the LSPs has been learnt on clean speech training data. In our approach parameters and speech samples are processed at different time scales by assuming the parameters to be constant for small blocks of data. Further enhancement is obtained by an iteration which can be applied on these small blocks. The experiments show that similar SNR gains are obtained as with the Kalman-LM-iterative algorithm. However better values of the noise level and the log-spectral distance are achieved

Keywords

Kalman filters; iterative methods; particle filtering (numerical methods); speech enhancement; Kalman filter; Kalman-LM-iterative algorithm; SNR gains; clean speech training data; iterative speech enhancement; line spectral pair parameters; log-spectral distance; marginalized particle filter; noise level; nonlinear dynamic state speech model; single channel speech enhancement; speech samples; Iterative algorithms; Nonlinear dynamical systems; Parameter estimation; Particle filters; Particle tracking; Signal to noise ratio; Speech enhancement; State estimation; State-space methods; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on

Conference_Location

Toulouse

ISSN

1520-6149

Print_ISBN

1-4244-0469-X

Type

conf

DOI

10.1109/ICASSP.2006.1660058

Filename

1660058