Tone modeling using stress information for HMM-based Thai speech synthesis

Decha Moungsri, Tomoki Koriyama, Takashi Nose, Takao Kobayashi

Research output: Contribution to journalConference article

4 Citations (Scopus)

Abstract

This paper describes a modeling technique of Thai tones for HMM-based speech synthesis. Tones are important prosodic features for tonal languages including Thai because the phonetically same words but with different tones give different meanings. Although there have been several approaches to improving tone correctness of synthetic speech by considering tone types, another significant factor, stress, was not used explicitly for prosody modeling. We incorporate stress/unstress information into the framework of the HMM-based speech synthesis. Objective and subjective evaluation results show that the use of stress information improves the performance in Thai tone modeling.

Original languageEnglish
Pages (from-to)1057-1061
Number of pages5
JournalProceedings of the International Conference on Speech Prosody
DOIs
Publication statusPublished - 2014
Event7th International Conference on Speech Prosody, SP 2014 - Dublin, Ireland
Duration: 2014 May 202014 May 23

Keywords

  • Context clustering
  • HMM-based speech synthesis
  • Stress
  • Tone correctness

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint Dive into the research topics of 'Tone modeling using stress information for HMM-based Thai speech synthesis'. Together they form a unique fingerprint.

  • Cite this