Research on HMM_based speech synthesis for Lhasa dialect

Author

Lu, Gao ; Hongzhi, Yu ; Jinshuang, Zhang ; Huaping, Fang

Author_Institution

Key Lab. of China´´s Nat. Linguistic Inf. Technol., Northwest Univ. for Nat., Lanzhou, China

fYear

2011

fDate

21-23 Oct. 2011

Firstpage

429

Lastpage

433

Abstract

Based on HMM synthesis system, the paper has applied the principles into Tibetan Lhasa dialect, and completed HMM-based Lhasa speech synthesis system. This paper describes in detail the synthesis corpus construction, context feature labeling, questionnaire design and etc. as data preparations. Meanwhile, under the HTS2.0 platform, it also elaborates the training model and speech synthesis model in Tibetan speech synthesis to build a HMM-based speech synthesis system to realize the diversification of minority languages speech signal processing technologies.

Keywords

hidden Markov models; natural language processing; speech synthesis; HMM based speech synthesis; HTS 2.0 platform; Tibetan Lhasa dialect; context feature labeling; minority languages speech signal processing technologies; questionnaire design; synthesis corpus construction; Context; Hidden Markov models; High temperature superconductors; Labeling; Speech; Speech synthesis; Training; Data preparation; HTS; Speech synthesis; Tibetan; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis and Signal Processing (IASP), 2011 International Conference on

Conference_Location

Hubei

Print_ISBN

978-1-61284-879-2

Type

conf

DOI

10.1109/IASP.2011.6109077

Filename

6109077