Chinese-Tibetan cross-language voice conversion method and system

Abstract

The invention discloses a Chinese-Tibetan cross-language voice conversion method, and the method comprises the following steps: A, carrying out the cutting and marking, element classification and catalogue indexing of a voice corpus through designing a corresponding text corpus and recording the voice corpus, and completing the building of a Tibetan Lhasa dialect syllable database and a standard Chinese prosodic feature analysis database; B, building a fundamental frequency model through employing a five-degree tone model, building a duration conversion model and a pause duration conversion model and completing the building of a rhythm model; C, inputting a Tibetan text, selecting proper syllables from the built Tibetan Lhasa dialect syllable database through employing a decision tree, and completing the voice conversion based on the technology of waveform splicing technology; D, carrying out the modification of rhythm parameters (fundamental frequency, duration and pause duration) of the converted voice through employing a STRAIGHT algorithm, completing the rhythm control, and outputting standard Chinese voices. The method achieves a Chinese-Tibetan cross-language voice conversion system based on rhythm control.

Description

technical field [0001] The invention belongs to the technical field of multilingual speech synthesis, and in particular relates to a Chinese-Tibetan bilingual cross-language speech conversion method and system thereof. Background technique [0002] With the rapid development of science and technology, artificial intelligence has gradually entered people's lives, and voice conversion technology is an important part of artificial intelligence technology, so voice conversion technology is an important research direction in the field of scientific research. Speech conversion technology is a relatively new research direction of artificial intelligence. It is a method of modifying the speech characteristics of the source speaker to make it have the speech characteristics of the target speaker. Same-language speech conversion means that the source speaker and the target speaker speak the same language, and cross-language speech conversion means that the source speaker and the targe...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of low naturalness and poor intelligibility in the cross-language speech conversion existing in the prior art, the present invention provides a Chinese-Tibetan bilingual cross-language speech conversion method and system, mainly for Tibetan to Chinese The prosody method of cross-language speech conversion has been researched and finally realized the cross-language conversion of Chinese and Tibetan bilinguals, which will not only promote the rapid development of Tibetan speech information processing technology, but also play a vital role in promoting the communication of speech technology between ethnic groups

Images