HMM speech recognition with reduced training

One of the problems faced in automatic speech recognition is the amount of training required to adapt the machine to the speaker way of pronunciation. To a certain extent, the accuracy of correct recognition is proportional to the amount of training and adaptation carried out. This is especially tru...

Full description

Saved in:

Bibliographic Details
Main Authors:	Foo, Say Wei, Yap, Timothy
Other Authors:	School of Electrical and Electronic Engineering
Format:	Conference or Workshop Item
Language:	English
Published:	2009
Subjects:	DRNTU::Engineering::Electrical and electronic engineering::Electronic circuits
Online Access:	https://hdl.handle.net/10356/91395 http://hdl.handle.net/10220/4687
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-91395
record_format	dspace
spelling	sg-ntu-dr.10356-913952020-03-07T13:24:46Z HMM speech recognition with reduced training Foo, Say Wei Yap, Timothy School of Electrical and Electronic Engineering IEEE International Conference on Information, Communications and Signal Processing (1st : 1997 : Singapore) DRNTU::Engineering::Electrical and electronic engineering::Electronic circuits One of the problems faced in automatic speech recognition is the amount of training required to adapt the machine to the speaker way of pronunciation. To a certain extent, the accuracy of correct recognition is proportional to the amount of training and adaptation carried out. This is especially true when a large vocabulary is involved. For cerlain applications, it is desirable that the training requirement be reduced to the bare minimum without sacrificing the accuracy of recognition. In this paper, the minimum number of training required to achieve an acceptable degree of accuracy for a speaker dependent speech recognition system based on the Hidden Markov Model (HMM) is investigated. A method is also proposed which retains the same degree of accuracy of recognition with much reduced training. Published version 2009-07-21T08:15:03Z 2019-12-06T18:04:55Z 2009-07-21T08:15:03Z 2019-12-06T18:04:55Z 1997 1997 Conference Paper Foo, S. W. & Yap, T. (1997). HMM speech recognition with reduced training. Proceedings of the International Conference on Information, Communications and Signal Processing 1997: (pp. 1016-1019). https://hdl.handle.net/10356/91395 http://hdl.handle.net/10220/4687 10.1109/ICICS.1997.652134 en © 1997 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. 4 p. application/pdf
institution	Nanyang Technological University
building	NTU Library
country	Singapore
collection	DR-NTU
language	English
topic	DRNTU::Engineering::Electrical and electronic engineering::Electronic circuits
spellingShingle	DRNTU::Engineering::Electrical and electronic engineering::Electronic circuits Foo, Say Wei Yap, Timothy HMM speech recognition with reduced training
description	One of the problems faced in automatic speech recognition is the amount of training required to adapt the machine to the speaker way of pronunciation. To a certain extent, the accuracy of correct recognition is proportional to the amount of training and adaptation carried out. This is especially true when a large vocabulary is involved. For cerlain applications, it is desirable that the training requirement be reduced to the bare minimum without sacrificing the accuracy of recognition. In this paper, the minimum number of training required to achieve an acceptable degree of accuracy for a speaker dependent speech recognition system based on the Hidden Markov Model (HMM) is investigated. A method is also proposed which retains the same degree of accuracy of recognition with much reduced training.
author2	School of Electrical and Electronic Engineering
author_facet	School of Electrical and Electronic Engineering Foo, Say Wei Yap, Timothy
format	Conference or Workshop Item
author	Foo, Say Wei Yap, Timothy
author_sort	Foo, Say Wei
title	HMM speech recognition with reduced training
title_short	HMM speech recognition with reduced training
title_full	HMM speech recognition with reduced training
title_fullStr	HMM speech recognition with reduced training
title_full_unstemmed	HMM speech recognition with reduced training
title_sort	hmm speech recognition with reduced training
publishDate	2009
url	https://hdl.handle.net/10356/91395 http://hdl.handle.net/10220/4687
_version_	1681049210282049536

HMM speech recognition with reduced training

Similar Items