Research on Prosodic Features and Their Prediction Issues in Uyghur Text-to-Speech System

Abstract

As one of the core technologies of minority language information processing, in recent years, the Uyghur speech synthesis technology has made great progress, but in TTS (Text To Speech) systems, prosodic phrases are not predicted with high accuracy which slows down the improvement of naturalness of synthesized speech. In this paper, Uyghur prosodic features was studied and the Context features which affects the Uyghur Prosodic phrases was analyzed on the basis of Uyghur prosodic features and large Uyghur speech Corpus. The context parameters that have an important impact on Uyghur prosodic features were collected and question sets well fits the training of Uyghur prosodic prediction was designed, and the training data was prepared. Consequently, the Uyghur prosodic training was processed and how to further apply it in the Uyghur speech synthesis system to attain higher naturalness was discussed.