NDLI: Improving robustness of deep neural network acoustic models via speech separation and joint adaptive training

Content Provider	ACM Digital Library
Author	Wang, DeLiang Narayanan, Arun
Copyright Year	2015
Abstract	Although deep neural network (DNN) acoustic models are known to be inherently noise robust, especially with matched training and testing data, the use of speech separation as a frontend and for deriving alternative feature representations has been shown to improve performance in challenging environments. We first present a supervised speech separation system that significantly improves automatic speech recognition (ASR) performance in realistic noise conditions. The system performs separation via ratio time-frequency masking; the ideal ratio mask (IRM) is estimated using DNNs. We then propose a framework that unifies separation and acoustic modeling via joint adaptive training. Since the modules for acoustic modeling and speech separation are implemented using DNNs, unification is done by introducing additional hidden layers with fixed weights and appropriate network architecture. On the CHiME-2 medium-large vocabulary ASR task, and with log mel spectral features as input to the acoustic model, an independently trained ratio masking frontend improves word error rates by 10.9% (relative) compared to the noisy baseline. In comparison, the jointly trained system improves performance by 14.4%. We also experiment with alternative feature representations to augment the standard log mel features, like the noise and speech estimates obtained from the separation module, and the standard feature set used for IRM estimation. Our best system obtains a word error rate of 15.4% (absolute), an improvement of 4.6 percentage points over the next best result on this corpus.
Starting Page	92
Ending Page	101
Page Count	10
File Format	PDF
ISSN	23299290
e-ISSN	23299304
DOI	10.1109/TASLP.2014.2372314
Volume Number	23
Issue Number	1
Journal	IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2015-01-01
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	CHiME-2 Joint training Ratio masking Robust ASR Time-frequency masking
Content Type	Text
Resource Type	Article
Subject	Instrumentation Computational Mathematics Signal Processing Electrical and Electronic Engineering Acoustics and Ultrasonics Speech and Hearing Media Technology

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Improving Robustness of Deep Neural Network Acoustic Models via Speech Separation and Joint Adaptive Training

A joint training framework for robust automatic speech recognition

Improving Robustness of Deep Neural Network Acoustic Models via Speech Separation and Joint Adaptive Training

Joint noise adaptive training for robust automatic speech recognition

Investigation of Speech Separation as a Front-End for Noise Robust Speech Recognition

Investigation of speech separation as a front-end for noise robust speech recognition

Complex ratio masking for monaural speech separation

A spectral masking approach to noise-robust speech recognition using deep neural networks

Joint optimization of masks and deep recurrent neural networks for monaural source separation

Improving robustness of deep neural network acoustic models via speech separation and joint adaptive training

Similar Documents

Improving Robustness of Deep Neural Network Acoustic Models via Speech Separation and Joint Adaptive Training

A joint training framework for robust automatic speech recognition

Improving Robustness of Deep Neural Network Acoustic Models via Speech Separation and Joint Adaptive Training

Joint noise adaptive training for robust automatic speech recognition

Investigation of Speech Separation as a Front-End for Noise Robust Speech Recognition

Investigation of speech separation as a front-end for noise robust speech recognition

Complex ratio masking for monaural speech separation

A spectral masking approach to noise-robust speech recognition using deep neural networks

Joint optimization of masks and deep recurrent neural networks for monaural source separation

Improving robustness of deep neural network acoustic models via speech separation and joint adaptive training