Clap your hands! Calibrating spectral subtraction for dereverberation

Reverberation effects as observed by room microphones severely degrade the performance of automatic speech recognition systems. We investigate the use of dereverberation by spectral subtraction as proposed by Lebart and Boucher and introduce a simple approach to estimate the required decay parameter...

Full description

Saved in:
Bibliographic Details
Main Authors: Zah, U, Riedhammer, K, Bocklet, T, Noth, E
Format: Conference Proceeding
Language:English
Subjects:
Aging
Automatic speech recognition
Feature extraction
Hidden Markov models
Microphones
Performance loss
Reverberation
Robustness
Speech analysis
Speech recognition
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Reverberation effects as observed by room microphones severely degrade the performance of automatic speech recognition systems. We investigate the use of dereverberation by spectral subtraction as proposed by Lebart and Boucher and introduce a simple approach to estimate the required decay parameter by clapping hands. Experiments on small vocabulary continuous speech recognition task on read speech show that using the calibrated dereverberation improves WER from 73.2 to 54.7 for the best microphone. In combination with system adaptation, the WER could be reduced to 28.2, which is only a 16% relative loss of performance comparison to using a headset instead of a room microphone.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2010.5495687