Formulation of the REMOS concept from an uncertainty decoding perspective

Conference contribution
(Conference Contribution)


Publication Details

Author(s): Maas R, Sehr A, Yoshioka T, Delcroix M, Kinoshita K, Nakatani T, Kellermann W
Publication year: 2013
Pages range: 1-6
ISBN: 978-1-4673-5807-1
Language: English


Abstract


In this paper, we introduce a new formulation of the REMOS (REverberation MOdeling for Speech recognition) concept from an uncertainty decoding perspective. Based on a convolutive observation model that relaxes the conditional independence assumption of hidden Markov models, REMOS effectively adapts automatic speech recognition (ASR) systems to noisy and strongly reverberant environments. While uncertainty decoding approaches are typically designed to operate irrespectively of the employed decoding routine of the ASR system, REMOS explicitly considers the additional information provided by the Viterbi decoder. In contrast to previous publications of the REMOS concept, we provide a conclusive derivation of its decoding routine using a Bayesian network representation in order to prove its inherent uncertainty decoding character. © 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)
Nippon Telegraph and Telephone (NTT) / 日本電信電話株式会社


How to cite

APA:
Maas, R., Sehr, A., Yoshioka, T., Delcroix, M., Kinoshita, K., Nakatani, T., & Kellermann, W. (2013). Formulation of the REMOS concept from an uncertainty decoding perspective. (pp. 1-6). Santorini, GR.

MLA:
Maas, Roland, et al. "Formulation of the REMOS concept from an uncertainty decoding perspective." Proceedings of the International Conference on Digital Signal Processing (DSP), Santorini 2013. 1-6.

BibTeX: 

Last updated on 2018-04-12 at 20:53