Frame-wise HMM adaptation using state-dependent reverberation estimates

Conference contribution
(Conference Contribution)


Publication Details

Author(s): Sehr A, Maas R, Kellermann W
Publication year: 2011
Pages range: 5484-5487
ISBN: 9781457705397
ISSN: 2379-190X
Language: English


Abstract


A novel frame-wise model adaptation approach for reverberation-robust distant-talking speech recognition is proposed. It adjusts the means of static cepstral features to capture the statistics of reverberant feature vector sequences obtained from distant-talking speech recordings. The means of the HMMs are adapted during decoding using a state-dependent estimate of the late reverberation determined by joint use of a feature-domain reverberation model and optimum partial state sequences. Since the parameters of the HMMs and the reverberation model can be estimated completely independently, the approach is very flexible with respect to changing acoustic environments. Due to the frame-wise model adaptation, some of the HMM limitations are relieved, and recognition results surpassing that of matched reverberant training are obtained at the cost of a moderately increased decoding complexity. © 2011 IEEE.


FAU Authors / FAU Editors

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


How to cite

APA:
Sehr, A., Maas, R., & Kellermann, W. (2011). Frame-wise HMM adaptation using state-dependent reverberation estimates. In Proceedings of the 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 (pp. 5484-5487). Prague, CZ.

MLA:
Sehr, Armin, Roland Maas, and Walter Kellermann. "Frame-wise HMM adaptation using state-dependent reverberation estimates." Proceedings of the 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011, Prague 2011. 5484-5487.

BibTeX: 

Last updated on 2019-28-04 at 15:53