Research on HMM_based speech synthesis for Lhasa dialect

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.