Method for carrying out hierarchical modeling and predicating on mandarin accent

Abstract

The invention discloses a method for carrying out hierarchical modeling and predicating on mandarin accent, which is used for describing the mandarin accent by adopting a hierarchical accent description system. The method comprises the following steps of: selecting an appropriate accent description system and creating a hierarchy-labeled accent corpus; generating a prosodic word accent prediction model through training; generating a sentence accent prediction model through training; and comprehensively generating an accent labeling result of each syllable according to the prosodic word accent model and the sentence accent model. According to the invention, the fineness of the accent model is improved, meanwhile, higher accent prediction correctness and recall ratio are also ensured, the naturalness and expressive force of synthetic speech are further improved, the accent phenomenon of rhythm highlight can be represented by more accurate description speech, and a finer accent hierarchy labeling result can be acquired from any input text.

Description

technical field [0001] The present invention relates to the technical field of speech synthesis in human-computer interaction, in particular to a method for hierarchically modeling and predicting stress in Mandarin, in particular to the modeling of sentence stress and word stress in Mandarin, and word stress based on the maximum entropy model , A two-layer stress prediction method for sentence stress. Background technique [0002] Accurate stress description and prediction of stress information from text information have always been a crucial step in speech synthesis, and are an important part of improving the expressiveness of synthesized speech and building a harmonious human-computer interaction technology. The accent model can describe the cadence and priority of the speech, thereby improving the expressiveness and naturalness of the synthesized speech. The modeling and prediction of accent is of great significance to the development of speech synthesis, human-computer ...

AI Technical Summary

Problems solved by technology

However, from the experimental results of speech synthesis, one of the important reasons why the synthesis results are not ideal is that the existing synthesis system ignores the problem of soft voice

Images