Kalman filter for speech enhancement in cocktail party scenarios using a codebook-based approach

Enhancement of speech in non-stationary background noise is a challenging task, and conventional single channel speech enhancement algorithms have not been able to improve the speech intelligibility in such scenarios. The work proposed in this paper investigates a single channel Kalman filter based...

Full description

Saved in:
Bibliographic Details
Main Authors: Kavalekalam, Mathew Shaji, Christensen, Mads Grosboll, Gran, Fredrik, Boldt, Jesper B.
Format: Conference Proceeding
Language:English
Subjects:
Algorithms
Approximation algorithms
autoregressive models
Channels
Conferences
Estimation
Intelligibility
kalman filter
Kalman filters
Noise measurement
Speech
Speech coding
Speech enhancement
Speech processing
Tasks
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Enhancement of speech in non-stationary background noise is a challenging task, and conventional single channel speech enhancement algorithms have not been able to improve the speech intelligibility in such scenarios. The work proposed in this paper investigates a single channel Kalman filter based speech enhancement algorithm, whose parameters are estimated using a codebook based approach. The results indicate that the enhancement algorithm is able to improve the speech intelligibility and quality according to objective measures. Moreover, we investigate the effects of utilizing a speaker specific trained codebook over a generic speech codebook in relation to the performance of the speech enhancement system.
ISSN:2379-190X
DOI:10.1109/ICASSP.2016.7471663