Universiti Teknologi Malaysia Institutional Repository

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

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

[img]
Preview
PDF
207kB

Official URL: http://dx.doi.org/10.5897/sre11.931

Abstract

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.

Item Type:Article
Uncontrolled Keywords:corpus based, Heuristic method, simulated annealing, speech concatenation
Subjects:Q Science > Q Science (General)
Divisions:Biosciences and Medical Engineering
ID Code:29907
Deposited By: Yanti Mohd Shah
Deposited On:21 Apr 2013 03:32
Last Modified:22 Oct 2020 04:07

Repository Staff Only: item control page