Uncertainty decoding for DNN-HMM hybrid systems based on numerical sampling

Conference contribution
(Conference Contribution)


Publication Details

Author(s): Hümmer C, Maas R, Schwarz A, Astudillo RF, Kellermann W
Publisher: International Speech and Communication Association
Publication year: 2015
Pages range: 3556-3560


Abstract


In this article, we propose an uncertainty decoding scheme for DNN-HMM hybrid systems based on numerical sampling. A finite set of samples is drawn from the estimated probability distribution of the acoustic features and subsequently passed through feature transformations/extensions and the deep neural network (DNN). Then, the nonlinearly-transformed feature samples are averaged at the output of the DNN in order to approximate the posterior distribution of the context-dependent Hidden Markov Model (HMM) states. This concept is experimentally verified for the REVERB challenge task using a reverberation-robust DNN-HMM hybrid system: The numerical sampling is performed in the logmelspec domain, where we estimate the posterior distribution of the acoustic features by combining coherence-based Wiener filtering and uncertainty propagation. The experimental results highlight the good performance of the proposed uncertainty decoding scheme with significantly increased recognition accuracy even for a small number of feature samples.



FAU Authors / FAU Editors

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


External institutions
Instituto de Engenharia de Sistemas e Computadores, Investigação e Desenvolvimento em Lisboa (INESC-ID)


How to cite

APA:
Hümmer, C., Maas, R., Schwarz, A., Astudillo, R.F., & Kellermann, W. (2015). Uncertainty decoding for DNN-HMM hybrid systems based on numerical sampling. (pp. 3556-3560). Dresden, DE: International Speech and Communication Association.

MLA:
Hümmer, Christian, et al. "Uncertainty decoding for DNN-HMM hybrid systems based on numerical sampling." Proceedings of the 16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015, Dresden International Speech and Communication Association, 2015. 3556-3560.

BibTeX: 

Last updated on 2018-10-08 at 08:54