A novel model-based pitch conversion method for Mandarin speech

Hsin Te Hwang*, Chen Yu Chiang, Po Yi Sung, Sin-Horng Chen

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

Abstract

In this paper, a novel model-based pitch conversion method for Mandarin is presented and compared with other two conventional conversion methods, i.e. the mean/variance transformation approach and the GMM-based mapping approach. Syllable pitch contour is first quantized by 3 rd order orthogonal expansion coefficients; then, the source and target speakers' prosodic models are constructed, respectively. Two mapping methods based on the prosodic model are presented. Objective tests confirmed that one of the proposed methods are superior the conventional methods. Some findings in informal listening tests and objective tests are worthwhile to further investigate.

Original languageEnglish
Pages (from-to)2643-2646
Number of pages4
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
StatePublished - 26 Nov 2009
Event10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 - Brighton, United Kingdom
Duration: 6 Sep 200910 Sep 2009

Keywords

  • Pitch conversion
  • Prosodic model
  • Prosody conversion
  • Voice conversion

Fingerprint

Dive into the research topics of 'A novel model-based pitch conversion method for Mandarin speech'. Together they form a unique fingerprint.

Cite this