Sehr A, Kellermann W (2008)
Publication Language: English
Publication Status: Published
Publication Type: Conference contribution, Conference Contribution
Publication year: 2008
Pages Range: 783-787
Article Number: 5074516
Event location: Pacific Grove, CA
ISBN: 9781424429417
DOI: 10.1109/ACSSC.2008.5074516
A model-based dereverberation approach for robust distant-talking speech recognition employing the powerful acoustic model of the recognizer to describe the clean speech feature sequence is discussed. The clean speech model is combined with a statistical reverberation model describing the acoustic path between speaker and microphone directly in the mel-spectral domain. Dereverberation is performed during recognition bydetermining the most likely contributions of the combined model's components to the current reverberant feature vector. The advantages of processing feature-domain representations of speech rather than using time- or frequency-domain speech representations are the dimension reduction and the possibility to obtain robust reverberation models valid for arbitrary speaker and microphone positions in the recording room. In this contribution, we emphasize that the criterion used for the dereverberation operation is equivalent to maximum a posteriori estimation. Connected-digit recognition experiments confirm the superior performance of the novel concept. © 2008 IEEE.
APA:
Sehr, A., & Kellermann, W. (2008). Model-based dereverberation of speech in the mel-spectral domain. In Proceedings of the 2008 42nd Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2008 (pp. 783-787). Pacific Grove, CA, US.
MLA:
Sehr, Armin, and Walter Kellermann. "Model-based dereverberation of speech in the mel-spectral domain." Proceedings of the 2008 42nd Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2008, Pacific Grove, CA 2008. 783-787.
BibTeX: Download