An uncertainty decoding approach to noise- and reverberation-robust speech recognition

Conference contribution
(Conference Contribution)


Publication Details

Author(s): Maas R, Thippur A, Sehr A, Kellermann W
Publication year: 2013
Pages range: 7388-7392
ISBN: 978-1-4799-0356-6
ISSN: 2379-190X
Language: English


Abstract


The generic REMOS (REverberation MOdeling for robust Speech recognition) concept is extended in this contribution to cope with additional noise components. REMOS originally embeds an explicit reverberation model into a hiddenMarkov model (HMM) leading to a relaxed conditional independence assumption for the observed feature vectors. During recognition, a nonlinear optimization problem is to be solved in order to adapt the HMMs' output probability density functions to the current reverberation conditions. The extension for additional noise components necessitates a modified numerical solver for the nonlinear optimization problem. We propose an approximation scheme based on continuous piecewise linear regression. Connected-digit recognition experiments demonstrate the potential of REMOS in reverberant and noisy environments. They furthermore reveal that the benefit of an explicit reverberation model, overcoming the conditional independence assumption, increases with increasing signal-to-noise-ratios. © 2013 IEEE.


FAU Authors / FAU Editors

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


External institutions
Hochschule für Technik und Wirtschaft Berlin (HTW)
Royal Institute of Technology / Kungliga Tekniska Högskolan (KTH)


How to cite

APA:
Maas, R., Thippur, A., Sehr, A., & Kellermann, W. (2013). An uncertainty decoding approach to noise- and reverberation-robust speech recognition. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (pp. 7388-7392). Vancouver, BC, CA.

MLA:
Maas, Roland, et al. "An uncertainty decoding approach to noise- and reverberation-robust speech recognition." Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, BC 2013. 7388-7392.

BibTeX: 

Last updated on 2019-24-04 at 19:08