NDLI: Multitask Learning of Deep Neural Networks for Low-Resource Speech Recognition

Content Provider	IEEE Xplore Digital Library
Author	Dongpeng Chen Mak, B.K.-W.
Copyright Year	2014
Abstract	We propose a multitask learning (MTL) approach to improve low-resource automatic speech recognition using deep neural networks (DNNs) without requiring additional language resources. We first demonstrate that the performance of the phone models of a single low-resource language can be improved by training its grapheme models in parallel under the MTL framework. If multiple low-resource languages are trained together, we investigate learning a set of universal phones (UPS) as an additional task again in the MTL framework to improve the performance of the phone models of all the involved languages. In both cases, the heuristic guideline is to select a task that may exploit extra information from the training data of the primary task(s). In the first method, the extra information is the phone-to-grapheme mappings, whereas in the second method, the UPS helps to implicitly map the phones of the multiple languages among each other. In a series of experiments using three low-resource South African languages in the Lwazi corpus, the proposed MTL methods obtain significant word recognition gains when compared with single-task learning (STL) of the corresponding DNNs or ROVER that combines results from several STL-trained DNNs.
Starting Page	1172
Ending Page	1183
Page Count	12
File Size	1504742
File Format	PDF
ISSN	23299290
Volume Number	23
Issue Number	7
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2015-01-01
Publisher Place	U.S.A.
Access Restriction	One Nation One Subscription (ONOS)
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Acoustics Hidden Markov models Training Uninterruptible power systems Speech Data models Neural networks universal phone set Deep neural network (DNN) low-resource speech recognition multitask learning universal grapheme set
Content Type	Text
Resource Type	Article
Subject	Acoustics and Ultrasonics Signal Processing Instrumentation Speech and Hearing Electrical and Electronic Engineering Computational Mathematics 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

Multitask learning of deep neural networks for low-resource speech recognition

Investigation of maxout networks for speech recognition

Multi-lingual speech recognition with low-rank multi-task deep neural networks

Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers

Deep autoencoders augmented with phone-class feature for reverberant speech recognition

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

Deep maxout networks for low-resource speech recognition

Deep Neural Networks for Single-Channel Multi-Talker Speech Recognition

Chinese-English Phone Set Construction for Code-Switching ASR Using Acoustic and DNN-Extracted Articulatory Features

Multitask Learning of Deep Neural Networks for Low-Resource Speech Recognition

Similar Documents

Multitask learning of deep neural networks for low-resource speech recognition

Investigation of maxout networks for speech recognition

Multi-lingual speech recognition with low-rank multi-task deep neural networks

Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers

Deep autoencoders augmented with phone-class feature for reverberant speech recognition

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

Deep maxout networks for low-resource speech recognition

Deep Neural Networks for Single-Channel Multi-Talker Speech Recognition

Chinese-English Phone Set Construction for Code-Switching ASR Using Acoustic and DNN-Extracted Articulatory Features

Multitask Learning of Deep Neural Networks for Low-Resource Speech Recognition