Cover Image

Unit selection for Malay text-to-speech system using segmental context and simulated annealing

Unit selection method has become the main approach in speech synthesis. The increasing size of recorded speech has resulted in better synthesis speech quality but at the same time also resulted in more expensive computational effort. Therefore, this paper proposes a combination of segmental context...

Full description

Saved in:
Bibliographic Details
Main Authors: Tan, Tian Swee, Shaikh Salleh, Sheikh Hussain, Zainuddin, Zaitul Marlizawati, Lim, Yee Chea, Hum, Yan Chai
Format: Article
Language:English
Published: Academic Journals 2011
Subjects:
Q Science (General)
Online Access:http://eprints.utm.my/id/eprint/29907/1/TanTianSwee2011_UnitSelectionforMalayTexttospeechSystem.pdf
http://eprints.utm.my/id/eprint/29907/
http://dx.doi.org/10.5897/sre11.931
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.29907
record_format eprints
spelling my.utm.299072020-10-22T04:07:03Z http://eprints.utm.my/id/eprint/29907/ Unit selection for Malay text-to-speech system using segmental context and simulated annealing Tan, Tian Swee Shaikh Salleh, Sheikh Hussain Zainuddin, Zaitul Marlizawati Lim, Yee Chea Hum, Yan Chai Q Science (General) Unit selection method has become the main approach in speech synthesis. The increasing size of recorded speech has resulted in better synthesis speech quality but at the same time also resulted in more expensive computational effort. Therefore, this paper proposes a combination of segmental context matching procedure and Simulated Annealing (SA) in unit selection to improve the quality of synthetic speech and reduce the computational time. The process of unit selection is based on minimization of two costs: target cost and join cost. The segmental context (target cost), the first stage of unit selection matching procedure used to narrow down the search space, followed by an optimization method which is SA to find the units sequence with minimum join cost. Result shows that the synthesis words produced by the proposed system are 15.48% better compared to previous version of corpus-based Malay Text-to-Speech system. Future works may focus on combining SA with other heuristic methods to further enhancing the performance of unit selection. Academic Journals 2011-09-19 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/29907/1/TanTianSwee2011_UnitSelectionforMalayTexttospeechSystem.pdf Tan, Tian Swee and Shaikh Salleh, Sheikh Hussain and Zainuddin, Zaitul Marlizawati and Lim, Yee Chea and Hum, Yan Chai (2011) Unit selection for Malay text-to-speech system using segmental context and simulated annealing. Scientific Research and Essays, 6 (20). pp. 4281-4289. ISSN 1992-2248 http://dx.doi.org/10.5897/sre11.931 DOI:10.5897/sre11.931
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/
language English
topic Q Science (General)
spellingShingle Q Science (General)
Tan, Tian Swee
Shaikh Salleh, Sheikh Hussain
Zainuddin, Zaitul Marlizawati
Lim, Yee Chea
Hum, Yan Chai
Unit selection for Malay text-to-speech system using segmental context and simulated annealing
description Unit selection method has become the main approach in speech synthesis. The increasing size of recorded speech has resulted in better synthesis speech quality but at the same time also resulted in more expensive computational effort. Therefore, this paper proposes a combination of segmental context matching procedure and Simulated Annealing (SA) in unit selection to improve the quality of synthetic speech and reduce the computational time. The process of unit selection is based on minimization of two costs: target cost and join cost. The segmental context (target cost), the first stage of unit selection matching procedure used to narrow down the search space, followed by an optimization method which is SA to find the units sequence with minimum join cost. Result shows that the synthesis words produced by the proposed system are 15.48% better compared to previous version of corpus-based Malay Text-to-Speech system. Future works may focus on combining SA with other heuristic methods to further enhancing the performance of unit selection.
format Article
author Tan, Tian Swee
Shaikh Salleh, Sheikh Hussain
Zainuddin, Zaitul Marlizawati
Lim, Yee Chea
Hum, Yan Chai
author_facet Tan, Tian Swee
Shaikh Salleh, Sheikh Hussain
Zainuddin, Zaitul Marlizawati
Lim, Yee Chea
Hum, Yan Chai
author_sort Tan, Tian Swee
title Unit selection for Malay text-to-speech system using segmental context and simulated annealing
title_short Unit selection for Malay text-to-speech system using segmental context and simulated annealing
title_full Unit selection for Malay text-to-speech system using segmental context and simulated annealing
title_fullStr Unit selection for Malay text-to-speech system using segmental context and simulated annealing
title_full_unstemmed Unit selection for Malay text-to-speech system using segmental context and simulated annealing
title_sort unit selection for malay text-to-speech system using segmental context and simulated annealing
publisher Academic Journals
publishDate 2011
url http://eprints.utm.my/id/eprint/29907/1/TanTianSwee2011_UnitSelectionforMalayTexttospeechSystem.pdf
http://eprints.utm.my/id/eprint/29907/
http://dx.doi.org/10.5897/sre11.931
_version_ 1681489440171622400
score 13.211869

Similar Items