An improved uncertainty decoding scheme with weighted samples for multi-channel DNN-HMM hybrid systems

Conference contribution
(Conference Contribution)


Publication Details

Author(s): Kellermann W, Hümmer C, Astudillo RF
Publication year: 2017
Pages range: 31-35
ISBN: 978-1-5090-5925-6
Language: English


Abstract

In this paper, we improve a recently-proposed uncertainty decoding scheme for DNN-HMM (deep neural network - hidden Markov model) hybrid systems, which models acoustic features as random variables. This uncertainty decoding strategy averages DNN outputs produced by a finite set of feature samples to approximate the posterior likelihoods of the context-dependent HMM states. As main innovation, we propose a weighted (instead of arithmetic) DNN-output averaging based on a minimum classification error criterion and apply it to a new probabilistic distortion model for multi-channel front-end signal enhancement schemes. The experimental evaluation is performed on the 8-channel REVERB Challenge task using a DNN-HMM hybrid system with spatial filtering of the microphone signals. It is shown that the recognition accuracy of the DNN-HMM hybrid system improves by incorporating uncertainty decoding and that the proposed weighted DNN-output averaging further reduces the word error rate scores


FAU Authors / FAU Editors

Hümmer, Christian
Professur für Nachrichtentechnik
Kellermann, Walter Prof. Dr.-Ing.
Professur für Nachrichtentechnik


External institutions with authors

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


How to cite

APA:
Kellermann, W., Hümmer, C., & Astudillo, R.F. (2017). An improved uncertainty decoding scheme with weighted samples for multi-channel DNN-HMM hybrid systems. In Proceedings of the Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA) (pp. 31-35). San Francisco, US.

MLA:
Kellermann, Walter, Christian Hümmer, and Ramón Fernández Astudillo. "An improved uncertainty decoding scheme with weighted samples for multi-channel DNN-HMM hybrid systems." Proceedings of the Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), San Francisco 2017. 31-35.

BibTeX: 

Last updated on 2019-27-05 at 14:53