Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICASSP.2013.6639102
Title: Noise adaptive front-end normalization based on Vector Taylor Series for Deep Neural Networks in robust speech recognition
Authors: Li, B.
Sim, K.C. 
Keywords: Deep Neural Networks
Noise Robustness
Vector Taylor Series
Issue Date: 18-Oct-2013
Source: Li, B.,Sim, K.C. (2013-10-18). Noise adaptive front-end normalization based on Vector Taylor Series for Deep Neural Networks in robust speech recognition. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings : 7408-7412. ScholarBank@NUS Repository. https://doi.org/10.1109/ICASSP.2013.6639102
Abstract: Deep Neural Networks (DNNs) have been successfully applied to various speech tasks during recent years. In this paper, we investigate the use of DNNs for noise-robust speech recognition and demonstrate their superior capabilities of modeling acoustic variations over the conventional Gaussian Mixture Models (GMMs). We then propose to compensate the normalization front-end of the DNNs using the GMM-based Vector Taylor Series (VTS) model compensation technique, which has been successfully applied in the GMM-based ASR systems to handle noisy speech. To fully benefit from both the powerful modeling capability of the DNN and the effective noise compensation of the VTS, an adaptive training algorithm is further developed. The preliminary experimental results on the AURORA 2 task have demonstrated the effectiveness of our approach. The adaptively trained system has been shown to outperform the GMM-based VTS adaptive training by relatively 18.8% using the MFCC features and 21.9% using the FBank features. © 2013 IEEE.
Source Title: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
URI: http://scholarbank.nus.edu.sg/handle/10635/78256
ISBN: 9781479903566
ISSN: 15206149
DOI: 10.1109/ICASSP.2013.6639102
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

23
checked on Feb 21, 2018

Page view(s)

32
checked on Feb 17, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.