NDLI: Speaker Adaptation of Hybrid NN/HMM Model for Speech Recognition Based on Singular Value Decomposition

Content Provider	Springer Nature Link
Author	Xue, Shaofei Jiang, Hui Dai, Lirong Liu, Qingfeng
Copyright Year	2015
Abstract	Recently several speaker adaptation methods have been proposed for deep neural network (DNN) in many large vocabulary continuous speech recognition (LVCSR) tasks. However, only a few methods rely on tuning the connection weights in trained DNNs directly to optimize system performance since it is very prone to over-fitting especially when some class labels are missing in the adaptation data. In this paper, we propose a new speaker adaptation method for the hybrid NN/HMM speech recognition model based on singular value decomposition (SVD). We apply SVD on the weight matrices in trained DNNs and then tune rectangular diagonal matrices with the adaptation data. This alleviates the over-fitting problem via updating the weight matrices slightly by only modifying the singular values. We evaluate the proposed adaptation method in two standard speech recognition tasks, namely TIMIT phone recognition and large vocabulary speech recognition in the Switchboard task. Experimental results have shown that it is effective to adapt large DNN models using only a small amount of adaptation data. For example, recognition results in the Switchboard task have shown that the proposed SVD-based adaptation method may achieve up to 3-6 % relative error reduction using only a few dozens of adaptation utterances per speaker.
Starting Page	175
Ending Page	185
Page Count	11
File Format	PDF
ISSN	19398018
Journal	Journal of Signal Processing Systems
Volume Number	82
Issue Number	2
e-ISSN	19398115
Language	English
Publisher	Springer US
Publisher Date	2015-06-10
Publisher Place	New York
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Deep neural network (DNN) Hybrid DNN/HMM Speaker adaptation Singular value decomposition (SVD) Signal, Image and Speech Processing Circuits and Systems Electrical Engineering Image Processing and Computer Vision Pattern Recognition Computer Imaging, Vision, Pattern Recognition and Graphics
Content Type	Text
Resource Type	Article
Subject	Theoretical Computer Science Signal Processing Control and Systems Engineering Information Systems Modeling and Simulation Hardware and Architecture

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

Speaker adaptation of hybrid NN/HMM model for speech recognition based on singular value decomposition

Basis-Based Speaker Adaptation Using Partitioned HMM Mean Parameters of Training Speaker Models

Unsupervised speaker adaptation of deep neural network based on the combination of speaker codes and singular value decomposition for speech recognition

Speaker Adaptive Training Localizing Speaker Modules in DNN for Hybrid DNN-HMM Speech Recognizers

Direct adaptation of hybrid DNN/HMM model for fast speaker adaptation in LVCSR based on speaker code

Audio-Visual Speaker Recognition for Video Broadcast News

A watermarking algorithm based on chirp z-transform, discrete wavelet transform, and singular value decomposition

The Optimized Dictionary based Robust Speaker Recognition

Superpositional HMM-Based Intonation Synthesis Using a Functional F0 Model

Speaker Adaptation of Hybrid NN/HMM Model for Speech Recognition Based on Singular Value Decomposition

Similar Documents

Speaker adaptation of hybrid NN/HMM model for speech recognition based on singular value decomposition

Basis-Based Speaker Adaptation Using Partitioned HMM Mean Parameters of Training Speaker Models

Unsupervised speaker adaptation of deep neural network based on the combination of speaker codes and singular value decomposition for speech recognition

Speaker Adaptive Training Localizing Speaker Modules in DNN for Hybrid DNN-HMM Speech Recognizers

Direct adaptation of hybrid DNN/HMM model for fast speaker adaptation in LVCSR based on speaker code

Audio-Visual Speaker Recognition for Video Broadcast News

A watermarking algorithm based on chirp z-transform, discrete wavelet transform, and singular value decomposition

The Optimized Dictionary based Robust Speaker Recognition

Superpositional HMM-Based Intonation Synthesis Using a Functional F0 Model

Speaker Adaptation of Hybrid NN/HMM Model for Speech Recognition Based on Singular Value Decomposition