Examining the Combination of Multi-Band Processing and Channel Dropout for Robust Speech Recognition

Document identifier: oai:DiVA.org:ltu-76905
Access full text here:10.21437/Interspeech.2019-3215
Keyword: Natural Sciences, Computer and Information Sciences, Computer Sciences, Naturvetenskap, Data- och informationsvetenskap, Datavetenskap (datalogi), Multi-band processing, Band-dropout, Robust speech recognition, Aurora-4, Maskininlärning, Machine Learning
Publication year: 2019
Relevant Sustainable Development Goals (SDGs):
SDG 9 Industry, innovation and infrastructureSDG 3 Good health and wellbeing
The SDG label(s) above have been assigned by OSDG.ai

Abstract:

A pivotal question in Automatic Speech Recognition (ASR) is the robustness of the trained models. In this study, we investigate the combination of two methods commonly applied to increase the robustness of ASR systems. On the one hand, inspired by auditory experiments and signal processing considerations, multi-band band processing has been used for decades to improve the noise robustness of speech recognition. On the other hand, dropout is a commonly used regularization technique to prevent overfitting by keeping the model from becoming over-reliant on a small set of neurons. We hypothesize that the careful combination of the two approaches would lead to increased robustness, by preventing the resulting model from over-rely on any given band.

To verify our hypothesis, we investigate various approaches for the combination of the two methods using the Aurora-4 corpus. The results obtained corroborate our initial assumption, and show that the proper combination of the two techniques leads to increased robustness, and to significantly lower word error rates (WERs). Furthermore, we find that the accuracy scores attained here compare favourably to those reported recently on the clean training scenario of the Aurora-4 corpus.

Authors

György Kovács

Luleå tekniska universitet; EISLAB; MTA-SZTE Research Group on Artificial Intelligence, Szeged, Hungary
Other publications >>

László Tóth

Institute of Informatics, University of Szeged, Szeged, Hungary
Other publications >>

Dirk Van Compernolle

Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Belgium
Other publications >>

Marcus Liwicki

Luleå tekniska universitet; EISLAB
Other publications >>

Record metadata

Click to view metadata