职员浏览: Statistical parametric speech synthesis of Malay language using found training data

Statistical parametric speech synthesis of Malay language using found training data

The preparation of training data for statistical parametric speech synthesis can be sophisticated. To ensure the good quality of synthetic speech, high quality low noise recording must be prepared. The preparation of recording script can be also tremendous from words collection, words selection and...

全面介绍

Saved in:

书目详细资料
Main Authors:	Tan, Tian Swee, Yong, L. C.
格式:	Article
出版:	Maxwell Science Publications 2014
主题:	QH Natural history
在线阅读:	http://eprints.utm.my/id/eprint/62664/ http://www.maxwellsci.com/print/rjaset/v7-5143-5147.pdf
标签:	添加标签没有标签, 成为第一个标记此记录!

id	my.utm.62664
record_format	eprints
spelling	my.utm.626642017-06-01T02:59:13Z http://eprints.utm.my/id/eprint/62664/ Statistical parametric speech synthesis of Malay language using found training data Tan, Tian Swee Yong, L. C. QH Natural history The preparation of training data for statistical parametric speech synthesis can be sophisticated. To ensure the good quality of synthetic speech, high quality low noise recording must be prepared. The preparation of recording script can be also tremendous from words collection, words selection and sentences design. It requires tremendous human effort and takes a lot of time. In this study, we used alternative free source of recording and text such as audio-book, clean speech and so on as the training data. Some of the free source can provide high quality recording with low noise which is suitable to become training data. Statistical parametric speech synthesis method applying Hidden Markov Model (HMM) has been used. To test the reliability of synthetic speech, perceptual test has been conducted. The result of naturalness test is fairly reasonable. The intelligibility test showed encouraging result. The Word Error Rate (WER) for normal synthetic sentences is below 15% while for Semantically Unpredictable Sentences (SUS) is averagely in 30%. In short, using free and ready source as training data can leverage the process of preparing training data while obtaining motivating synthetic result. Maxwell Science Publications 2014 Article PeerReviewed Tan, Tian Swee and Yong, L. C. (2014) Statistical parametric speech synthesis of Malay language using found training data. Research Journal of Applied Sciences, Engineering and Technology, 7 (24). pp. 5143-5147. ISSN 2040-7459 http://www.maxwellsci.com/print/rjaset/v7-5143-5147.pdf
institution	Universiti Teknologi Malaysia
building	UTM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Teknologi Malaysia
content_source	UTM Institutional Repository
url_provider	http://eprints.utm.my/
topic	QH Natural history
spellingShingle	QH Natural history Tan, Tian Swee Yong, L. C. Statistical parametric speech synthesis of Malay language using found training data
description	The preparation of training data for statistical parametric speech synthesis can be sophisticated. To ensure the good quality of synthetic speech, high quality low noise recording must be prepared. The preparation of recording script can be also tremendous from words collection, words selection and sentences design. It requires tremendous human effort and takes a lot of time. In this study, we used alternative free source of recording and text such as audio-book, clean speech and so on as the training data. Some of the free source can provide high quality recording with low noise which is suitable to become training data. Statistical parametric speech synthesis method applying Hidden Markov Model (HMM) has been used. To test the reliability of synthetic speech, perceptual test has been conducted. The result of naturalness test is fairly reasonable. The intelligibility test showed encouraging result. The Word Error Rate (WER) for normal synthetic sentences is below 15% while for Semantically Unpredictable Sentences (SUS) is averagely in 30%. In short, using free and ready source as training data can leverage the process of preparing training data while obtaining motivating synthetic result.
format	Article
author	Tan, Tian Swee Yong, L. C.
author_facet	Tan, Tian Swee Yong, L. C.
author_sort	Tan, Tian Swee
title	Statistical parametric speech synthesis of Malay language using found training data
title_short	Statistical parametric speech synthesis of Malay language using found training data
title_full	Statistical parametric speech synthesis of Malay language using found training data
title_fullStr	Statistical parametric speech synthesis of Malay language using found training data
title_full_unstemmed	Statistical parametric speech synthesis of Malay language using found training data
title_sort	statistical parametric speech synthesis of malay language using found training data
publisher	Maxwell Science Publications
publishDate	2014
url	http://eprints.utm.my/id/eprint/62664/ http://www.maxwellsci.com/print/rjaset/v7-5143-5147.pdf
_version_	1643655486619254784
score	13.251813

Statistical parametric speech synthesis of Malay language using found training data

相似书籍