ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Robust raw waveform speech recognition using relevance weighted representations

Agrawal, P and Ganapathy, S (2020) Robust raw waveform speech recognition using relevance weighted representations. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 25-29 October 2020, Shanghai; China, pp. 1649-1653.

[img]
Preview
PDF
INTERSPEECH-Vol-2020-2020-1649-1653.pdf - Published Version

Download (1MB) | Preview
Official URL: https://dx.doi.org/10.21437/Interspeech.2020-2301

Abstract

Speech recognition in noisy and channel distorted scenarios is often challenging as the current acoustic modeling schemes are not adaptive to the changes in the signal distribution in the presence of noise. In this work, we develop a novel acoustic modeling framework for noise robust speech recognition based on relevance weighting mechanism. The relevance weighting is achieved using a sub-network approach that performs feature selection. A relevance sub-network is applied on the output of first layer of a convolutional network model operating on raw speech signals while a second relevance sub-network is applied on the second convolutional layer output. The relevance weights for the first layer correspond to an acoustic filterbank selection while the relevance weights in the second layer perform modulation filter selection. The model is trained for a speech recognition task on noisy and reverberant speech. The speech recognition experiments on multiple datasets (Aurora-4, CHiME-3, VOiCES) reveal that the incorporation of relevance weighting in the neural network architecture improves the speech recognition word error rates significantly (average relative improvements of 10 over the baseline systems). © 2020 ISCA

Item Type: Conference Paper
Additional Information: cited By 0; Conference of 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 ; Conference Date: 25 October 2020 Through 29 October 2020; Conference Code:165507
Keywords: Acoustic noise; Convolution; Convolutional neural networks; Modulation; Network architecture; Speech; Speech communication, Baseline systems; Convolutional networks; Filter-bank selections; Modulation filters; Multiple data sets; Noise robust speech recognition; Relevance weights; Signal distribution, Speech recognition
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Depositing User: Mr Parikshita Behera
Date Deposited: 12 Jan 2021 10:37
Last Modified: 12 Jan 2021 10:37
URI: http://eprints.iisc.ac.in/id/eprint/67642

Actions (login required)

View Item View Item