Duration-embedded Bi-HMM for expressive voice conversion

Chi Chun Hsia, Chung-Hsien Wu, Te Hsien Liu

研究成果: Paper同行評審

1 引文 斯高帕斯(Scopus)


This paper presents a duration-embedded Bi-HMM framework for expressive voice conversion. First, Ward's minimum variance clustering method is used to cluster all the conversion units (sub-syllables) in order to reduce the number of conversion models as well as the size of the required training database. The duration-embedded Bi-HMM trained with the EM algorithm is built for each sub-syllable class to convert the neutral speech into emotional speech considering the duration information. Finally, the prosodic cues are included in the modification of the spectrum-converted speech. The STRAIGHT algorithm is adopted for high-quality speech analysis and synthesis. Target emotions including happiness, sadness and anger are used. Objective and perceptual evaluations were conducted to compare the performance of the proposed approach with previous methods. The results show that the proposed method exhibits encouraging potential in expressive voice conversion.

出版狀態Published - 2005 十二月 1
事件9th European Conference on Speech Communication and Technology - Lisbon, Portugal
持續時間: 2005 九月 42005 九月 8


Other9th European Conference on Speech Communication and Technology

All Science Journal Classification (ASJC) codes

  • Engineering(all)

指紋 深入研究「Duration-embedded Bi-HMM for expressive voice conversion」主題。共同形成了獨特的指紋。