Hands-free speech recognition using a reverberation model

Hands-free speech recognition using a reverberation model (2006)

Cached

Download Links

by Armin Sehr , Marcus Zeller , Walter Kellermann

Venue:	in the feature domain,” Proc. European Signal Processing Conference (EUSIPCO
Citations:	3 - 1 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Hands-free speech recognition using a reverberation model	INFERENCE
AUTHOR NAME	Armin Sehr	SVM HeaderParse 0.2
AUTHOR AFFIL	Multimedia Communications and Signal Processing,; University of Erlangen-Nuremberg	SVM HeaderParse 0.2
AUTHOR ADDR	Cauerstr. 7, 91058 Erlangen, Germany	SVM HeaderParse 0.2
AUTHOR NAME	Marcus Zeller	SVM HeaderParse 0.2
AUTHOR AFFIL	Multimedia Communications and Signal Processing,; University of Erlangen-Nuremberg	SVM HeaderParse 0.2
AUTHOR ADDR	Cauerstr. 7, 91058 Erlangen, Germany	SVM HeaderParse 0.2
AUTHOR NAME	Walter Kellermann	SVM HeaderParse 0.2
AUTHOR AFFIL	Multimedia Communications and Signal Processing,; University of Erlangen-Nuremberg	SVM HeaderParse 0.2
AUTHOR ADDR	Cauerstr. 7, 91058 Erlangen, Germany	SVM HeaderParse 0.2
ABSTRACT	A novel approach for robust hands-free speech recognition in highly reverberant environments is proposed. Unlike conventional HMMbased concepts, it implicitly accounts for the statistical dependence of successive feature vectors due to the reverberation. This property is attained by a combined acoustic model consisting of a conventional HMM, modeling the clean speech, and a reverberation model. Since the HMM is independent of the acoustic environment, it needs to be trained only once using the usual Baum-Welch reestimation procedure. The training of the reverberation model is based on a set of room impulse responses for the corresponding acoustic environment and involves only a negligible computational effort. Thus, the recognizer can be adapted to new environments with moderate effort. In a simulation of an isolated digit recognition task in a highly reverberant room, the proposed method achieves a 60 % reduction of the word error rate compared to a conventional HMM trained on reverberant speech, at the cost of an increased decoding complexity. 1.	SVM HeaderParse 0.2
YEAR	2006	INFERENCE
VENUE	in the feature domain,” Proc. European Signal Processing Conference (EUSIPCO	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
CITATIONS	1 found	ParsCit 1.0