Malay statistical parametric speech synthesis with intelligibility improvement using artificial intelligence

Speech synthesis is important nowadays and could be a great aid in various applications. So it is important to build a simple, reliable, light-weight, ease of use speech synthesizer. However, conventional speech synthesizers require tedious human efforts to prepare high quality recorded database, an...

Full description

Saved in:

Bibliographic Details
Main Author:	Lau, Chee Yong
Format:	Thesis
Language:	English
Published:	2015
Subjects:	QH301 Biology
Online Access:	http://eprints.utm.my/id/eprint/77693/1/LauCheeYongPFBME2015.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.77693
record_format	uketd_dc
spelling	my-utm-ep.776932018-06-29T21:29:23Z Malay statistical parametric speech synthesis with intelligibility improvement using artificial intelligence 2015-01 Lau, Chee Yong QH301 Biology Speech synthesis is important nowadays and could be a great aid in various applications. So it is important to build a simple, reliable, light-weight, ease of use speech synthesizer. However, conventional speech synthesizers require tedious human efforts to prepare high quality recorded database, and the intelligibility of synthetic speech may decrease due to the appearance of polyphone (character with more than 1 pronunciation) because the speech synthesizer may not contain the definition of the polyphones. Moreover, the ready speech synthesizers in market are mostly built in Unit Selection method, which is large in database size and relying on Malay linguist knowledge. In this study, statistical parametric speech synthesis method has been adopted using lab speech and free speech data harvested online. The intelligibility improvement has been achieved using Active Learning and Feedforward Neural Network with Back-Propagation. The amount of training data used remained the same throughout this study. The result was evaluated using perception test. The listening test showed that the intelligibility of synthetic speech has been improved about 20%- 30% using the artificial intelligence technique. Volunteers were invited to take part in Active Learning experiment. The result showed no controversy between the result done by volunteers and the correct answer. In conclusion, a light-weight Malay speech synthesizer has been created without relying on Malay linguist knowledge. Using free source as training data can ease the human effort in preparing training database and using artificial intelligence technique can improve the intelligibility of synthetic speech under the same amount of training data used. 2015-01 Thesis http://eprints.utm.my/id/eprint/77693/ http://eprints.utm.my/id/eprint/77693/1/LauCheeYongPFBME2015.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:96409 phd doctoral Universiti Teknologi Malaysia, Faculty of Biosciences and Medical Engineering Faculty of Biosciences and Medical Engineering
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	QH301 Biology
spellingShingle	QH301 Biology Lau, Chee Yong Malay statistical parametric speech synthesis with intelligibility improvement using artificial intelligence
description	Speech synthesis is important nowadays and could be a great aid in various applications. So it is important to build a simple, reliable, light-weight, ease of use speech synthesizer. However, conventional speech synthesizers require tedious human efforts to prepare high quality recorded database, and the intelligibility of synthetic speech may decrease due to the appearance of polyphone (character with more than 1 pronunciation) because the speech synthesizer may not contain the definition of the polyphones. Moreover, the ready speech synthesizers in market are mostly built in Unit Selection method, which is large in database size and relying on Malay linguist knowledge. In this study, statistical parametric speech synthesis method has been adopted using lab speech and free speech data harvested online. The intelligibility improvement has been achieved using Active Learning and Feedforward Neural Network with Back-Propagation. The amount of training data used remained the same throughout this study. The result was evaluated using perception test. The listening test showed that the intelligibility of synthetic speech has been improved about 20%- 30% using the artificial intelligence technique. Volunteers were invited to take part in Active Learning experiment. The result showed no controversy between the result done by volunteers and the correct answer. In conclusion, a light-weight Malay speech synthesizer has been created without relying on Malay linguist knowledge. Using free source as training data can ease the human effort in preparing training database and using artificial intelligence technique can improve the intelligibility of synthetic speech under the same amount of training data used.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Lau, Chee Yong
author_facet	Lau, Chee Yong
author_sort	Lau, Chee Yong
title	Malay statistical parametric speech synthesis with intelligibility improvement using artificial intelligence
title_short	Malay statistical parametric speech synthesis with intelligibility improvement using artificial intelligence
title_full	Malay statistical parametric speech synthesis with intelligibility improvement using artificial intelligence
title_fullStr	Malay statistical parametric speech synthesis with intelligibility improvement using artificial intelligence
title_full_unstemmed	Malay statistical parametric speech synthesis with intelligibility improvement using artificial intelligence
title_sort	malay statistical parametric speech synthesis with intelligibility improvement using artificial intelligence
granting_institution	Universiti Teknologi Malaysia, Faculty of Biosciences and Medical Engineering
granting_department	Faculty of Biosciences and Medical Engineering
publishDate	2015
url	http://eprints.utm.my/id/eprint/77693/1/LauCheeYongPFBME2015.pdf
_version_	1747817809181671424

Malay statistical parametric speech synthesis with intelligibility improvement using artificial intelligence

Similar Items