Mandarin text-to-speech synthesis

Ren Hua Wang, Sin-Horng Chen, Jianhua Tao, Min Chu

Research output: Chapter in Book/Report/Conference proceedingChapter

2 Scopus citations

Abstract

This chapter introduces Mandarin Text-To-Speech (MTTS) synthesis. Beginning with a brief review on the development history of MTTS and attributes of MTTS, three main constituents of the technology are presented: 1) Text processing: word segmentation, disambiguation of polyphones, and analysis of rhythm structure; 2) prosodic processing: features of Mandarin prosody, and prosody prediction, and; 3) speech synthesis: parametric synthesis and concatenative synthesis. Finally perspectives and applications for MTTS synthesis are discussed in the final sections.

Original languageEnglish
Title of host publicationAdvances in Chinese Spoken Language Processing
PublisherWorld Scientific Publishing Co.
Pages99-124
Number of pages26
ISBN (Electronic)9789812772961
ISBN (Print)9812569049, 9789812569042
DOIs
StatePublished - 1 Jan 2006

Fingerprint Dive into the research topics of 'Mandarin text-to-speech synthesis'. Together they form a unique fingerprint.

  • Cite this

    Wang, R. H., Chen, S-H., Tao, J., & Chu, M. (2006). Mandarin text-to-speech synthesis. In Advances in Chinese Spoken Language Processing (pp. 99-124). World Scientific Publishing Co.. https://doi.org/10.1142/9789812772961_0005