Model-Based Speech Enhancement Using SNR Dependent MMSE Estimation

Authors:

Esch, T. ,  Vary, P.

Book Title:

Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Organization:

IEEE

Pages:

p.p. 4652-4655

Address:

Prague, Czech Republic

Date:

May. 2011

ISBN:

978-1-45770-539-7

Language:

English

Abstract

This contribution presents a modified Kalman filter approach for single channel speech enhancement which is operating in the frequency domain. In the first step, temporal correlation of successive frames is exploited yielding estimates of the current speech and noise DFT coefficients. This first prediction is updated in the second step applying an SNR dependent MMSE estimator which is adapted to the (measured) statistics of the speech prediction error signal. Objective measurements show consistent improvements compared to estimators which do not take into account the temporal correlation or the influence of the input SNR on the statistics of the prediction error signal.

Download

BibTeX

Copyright © by IEEE
esch11.pdf

© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

---