Distant-talking continuous speech recognition based on a novel reverberation model

Distant-talking continuous speech recognition based on a novel reverberation model (2006)

Cached

Download Links

by Armin Sehr , Marcus Zeller , Walter Kellermann

Venue:	in the feature domain,” Proc. INTERSPEECH
Citations:	10 - 9 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Distant-talking continuous speech recognition based on a novel 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 automatic speech recognition in highly reverberant environments, proposed in [1] for isolated word recognition, is extended to continuous speech recognition (CSR) in this paper. The approach is based on a combined acoustic model consisting of a network of clean speech HMMs and a reverberation model. Because the grammatical information and the information about the acoustic environment are strictly separated in the combined model, a high degree of flexibility for adapting the system to new tasks and new environments is attained. We show that virtually all known CSR search algorithms can be used for decoding the proposed combined model if a few extensions are added. In a simulation of a connected digit recognition task, the proposed method achieves more than 40 % reduction of the word error rate compared to a conventional HMM-based system trained on reverberant speech, at the cost of an increased decoding complexity. Index Terms: robust speech recognition, distant-talking speech recognition, dereverberation.	SVM HeaderParse 0.2
YEAR	2006	INFERENCE
VENUE	in the feature domain,” Proc. INTERSPEECH	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	769--772	INFERENCE
CITATIONS	11 found	ParsCit 1.0