Strategies for modeling reverberant speech in the feature domain
Sehr A, Kellermann W (2009)
Publication Language: English
Publication Status: Published
Publication Type: Conference contribution, Conference Contribution
Publication year: 2009
Pages Range: 3725-3728
Article Number: 4960436
Event location: Taipei
ISBN: 978-1-4244-2353-8
DOI: 10.1109/ICASSP.2009.4960436
Abstract
The length of the room impulse response characterizing the acoustic path between speaker and microphone is significantly larger than the length of the analysis window used for feature extraction in automatic speech recognition (ASR) systems. Therefore, reverberation caused by multi-path propagation of sound waves from the speaker to distant-talking microphones has a dispersive effect on speech feature sequences. This dispersive effect causes a mismatch between the input speech and the acoustic models of the recognizer, usually trained on clean speech, and leads to a significant reduction of recognition performance. In this contribution, different strategies for obtaining acoustic models capturing the dispersive effect of reverberation are investigated in terms of modeling accuracy, flexibility with respect to changing reverberation conditions, effort for obtaining the reverberation representation and decoding complexity. ©2009 IEEE.
Authors with CRIS profile
How to cite
APA:
Sehr, A., & Kellermann, W. (2009). Strategies for modeling reverberant speech in the feature domain. In Proceedings of the 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 (pp. 3725-3728). Taipei, CN.
MLA:
Sehr, Armin, and Walter Kellermann. "Strategies for modeling reverberant speech in the feature domain." Proceedings of the 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009, Taipei 2009. 3725-3728.
BibTeX: Download