NDLI: Learning hidden unit contributions for unsupervised acoustic model adaptation

Content Provider	ACM Digital Library
Author	Renals, Steve Li, Jinyu Swietojanski, Pawel
Copyright Year	2016
Abstract	This work presents a broad study on the adaptation of neural network acoustic models by means of learning hidden unit contributions (LHUC) ---a method that linearly re-combines hidden units in a speaker- or environment-dependent manner using small amounts of unsupervised adaptation data. We also extend LHUC to a speaker adaptive training (SAT) framework that leads to a more adaptable DNN acoustic model, working both in a speaker-dependent and a speaker-independent manner, without the requirements to maintain auxiliary speaker-dependent feature extractors or to introduce significant speaker-dependent changes to the DNN structure. Through a series of experiments on four different speech recognition benchmarks (TED talks, Switchboard, AMI meetings, and Aurora4) comprising 270 test speakers, we show that LHUC in both its test-only and SAT variants results in consistent word error rate reductions ranging from 5% to 23% relative depending on the task and the degree of mismatch between training and test data. In addition, we have investigated the effect of the amount of adaptation data per speaker, the quality of unsupervised adaptation targets, the complementarity to other adaptation techniques, one-shot adaptation, and an extension to adapting DNNs trained in a sequence discriminative manner.
Starting Page	1450
Ending Page	1463
Page Count	14
File Format	PDF
ISSN	23299290
e-ISSN	23299304
Volume Number	24
Issue Number	8
Journal	IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2016-08-01
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Adaptation Deep neural networks (DNNs) Factorisation Learning hidden unit contributions (lHUC)
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

Speaker Adaptive Training of Deep Neural Network Acoustic Models Using I-Vectors

Speaker adaptive training of deep neural network acoustic models using i-vectors

Learning spectral mapping for speech dereverberation and denoising

Neural network based pitch tracking in very noisy speech

Representation Learning for Single-Channel Source Separation and Bandwidth Extension

Neural Network Based Pitch Tracking in Very Noisy Speech

Binaural classification for reverberant speech segregation using deep neural networks

Cluster Adaptive Training for Deep Neural Network Based Acoustic Model

Learning Spectral Mapping for Speech Dereverberation and Denoising

Learning hidden unit contributions for unsupervised acoustic model adaptation

Similar Documents

Speaker Adaptive Training of Deep Neural Network Acoustic Models Using I-Vectors

Speaker adaptive training of deep neural network acoustic models using i-vectors

Learning spectral mapping for speech dereverberation and denoising

Neural network based pitch tracking in very noisy speech

Representation Learning for Single-Channel Source Separation and Bandwidth Extension

Neural Network Based Pitch Tracking in Very Noisy Speech

Binaural classification for reverberant speech segregation using deep neural networks

Cluster Adaptive Training for Deep Neural Network Based Acoustic Model

Learning Spectral Mapping for Speech Dereverberation and Denoising

Learning hidden unit contributions for unsupervised acoustic model adaptation