On the application of reverberation suppression to robust speech recognition

Maas R, Habets E, Sehr A, Kellermann W (2012)


Publication Language: English

Publication Status: Published

Publication Type: Conference contribution, Conference Contribution

Publication year: 2012

Pages Range: 297-300

Article Number: 6287875

Event location: Kyoto JP

ISBN: 9781467300469

DOI: 10.1109/ICASSP.2012.6287875

Abstract

In this paper, we study the effect of the design parameters of a single-channel reverberation suppression algorithm on reverberation-robust speech recognition. At the same time, reverberation compensation at the speech recognizer is investigated. The analysis reveals that it is highly beneficial to attenuate only the reverberation tail after approximately 50 ms while coping with the early reflections and residual late-reverberation by training the recognizer on moderately reverberant data. It will be shown that the overall system at its optimum configuration yields a very promising recognition performance even in strongly reverberant environments. Since the reverberation suppression algorithm is evidenced to significantly reduce the dependency on the training data, it allows for a very efficient training of acoustic models that are suitable for a wide range of reverberation conditions. Finally, experiments with an "ideal" reverberation suppression algorithm are carried out to cross-check the inferred guidelines. © 2012 IEEE.

Authors with CRIS profile

How to cite

APA:

Maas, R., Habets, E., Sehr, A., & Kellermann, W. (2012). On the application of reverberation suppression to robust speech recognition. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (pp. 297-300). Kyoto, JP.

MLA:

Maas, Roland, et al. "On the application of reverberation suppression to robust speech recognition." Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Kyoto 2012. 297-300.

BibTeX: Download