Distant-talking continuous speech recognition based on a novel reverberation model in the feature domain

Conference contribution
(Conference Contribution)


Publication Details

Author(s): Sehr A, Zeller M, Kellermann W
Publication year: 2006
Volume: 2
Pages range: 769-772
ISBN: 9781604234497
ISSN: 19909772
Language: English


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 rever-berant speech, at the cost of an increased decoding complexity.


FAU Authors / FAU Editors

Kellermann, Walter Prof. Dr.-Ing.
Professur für Nachrichtentechnik
Sehr, Armin Dr.-Ing.
Professur für Nachrichtentechnik
Zeller, Marcus
Lehrstuhl für Multimediakommunikation und Signalverarbeitung


How to cite

APA:
Sehr, A., Zeller, M., & Kellermann, W. (2006). Distant-talking continuous speech recognition based on a novel reverberation model in the feature domain. In Proceedings of the INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP (pp. 769-772). Pittsburgh, PA, US.

MLA:
Sehr, Armin, Marcus Zeller, and Walter Kellermann. "Distant-talking continuous speech recognition based on a novel reverberation model in the feature domain." Proceedings of the INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP, Pittsburgh, PA 2006. 769-772.

BibTeX: 

Last updated on 2019-29-05 at 19:23