NDLI: Speaker adaptation of context dependent deep neural networks

Content Provider	IEEE Xplore Digital Library
Author	Hank Liao
Copyright Year	2013
Description	Author affiliation: Google Inc., New York, NY, USA (Hank Liao)
Abstract	There has been little work on examining how deep neural networks may be adapted to speakers for improved speech recognition accuracy. Past work has examined using a discriminatively trained affine transformation of the input features applied at a frame level or the re-training of the entire shallow network for a specific speaker. This work explores how deep neural networks may be adapted to speakers by re-training the input layer, the output layer or the entire network. We look at how L2 regularization using weight decay to the speaker independent model improves generalization. Other training factors are examined including the role momentum plays and stochastic mini-batch versus batch training. While improvements are significant for smaller networks, the largest show little gain from adaptation on a large vocabulary mobile speech recognition task.
Starting Page	7947
Ending Page	7951
File Size	356622
Page Count	5
File Format	PDF
ISBN	9781479903566
ISSN	15206149
DOI	10.1109/ICASSP.2013.6639212
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2013-05-26
Publisher Place	Canada
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Hidden Markov models Adaptation models Acoustics Neural networks Training Speech Speech recognition Speaker adaptation Large vocabulary continuous speech recognition Multilayer perceptrons Deep neural networks
Content Type	Text
Resource Type	Article

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

Large vocabulary continuous speech recognition with context-dependent DBN-HMMS

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

Adaptation of context-dependent deep neural networks for automatic speech recognition

Proposing two speaker adaptaion methods for deep neural network based speech recognition systems

Deep and Wide: Multiple Layers in Automatic Speech Recognition

Speaker adaptive training for deep neural networks embedding linear transformation networks

Continuous speech recognition using multilayer perceptrons with hidden Markov models

Improving DNN speaker independence with I-vector inputs

KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition

Speaker adaptation of context dependent deep neural networks

Similar Documents

Large vocabulary continuous speech recognition with context-dependent DBN-HMMS

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

Adaptation of context-dependent deep neural networks for automatic speech recognition

Proposing two speaker adaptaion methods for deep neural network based speech recognition systems

Deep and Wide: Multiple Layers in Automatic Speech Recognition

Speaker adaptive training for deep neural networks embedding linear transformation networks

Continuous speech recognition using multilayer perceptrons with hidden Markov models

Improving DNN speaker independence with I-vector inputs

KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition

Speaker adaptation of context dependent deep neural networks