Adapting HMMS of distant-talking asr systems using feature-domain reverberation models

Conference contribution
(Conference Contribution)


Publication Details

Author(s): Sehr A, Gardill M, Kellermann W
Publication year: 2009
Pages range: 540-543
ISSN: 2219-5491
Language: English


Abstract


To capture the dispersive effect of reverberation by Hidden Markov Model (HMM)-based distant-talking speech recognition systems, adapting the means of the current HMM state based on the means of the preceding states has been suggested in [1]. In this contribution, we propose to incorporate the reverberation models of [2] into the adaptation approach to describe the effect of reverberation with higher accuracy. Connected-digit recognition experiments in three different rooms confirm that the suggested more accurate reverberation representation leads to a significant performance increase in all investigated environments. © EURASIP, 2009.


FAU Authors / FAU Editors

Gardill, Markus Dr.
Lehrstuhl für Technische Elektronik
Kellermann, Walter Prof. Dr.-Ing.
Professur für Nachrichtentechnik
Sehr, Armin Dr.-Ing.
Professur für Nachrichtentechnik


How to cite

APA:
Sehr, A., Gardill, M., & Kellermann, W. (2009). Adapting HMMS of distant-talking asr systems using feature-domain reverberation models. In Proceedings of the 17th European Signal Processing Conference, EUSIPCO 2009 (pp. 540-543). Glasgow, GB.

MLA:
Sehr, Armin, Markus Gardill, and Walter Kellermann. "Adapting HMMS of distant-talking asr systems using feature-domain reverberation models." Proceedings of the 17th European Signal Processing Conference, EUSIPCO 2009, Glasgow 2009. 540-543.

BibTeX: 

Last updated on 2019-08-05 at 17:23