Syllable splitting method of Tibetan language of Anduo

Abstract

The syllable division of Tibetan speech is an important part and essential link in Tibetan speech information processing, and lays the foundation for Tibetan speech recognition and speech database making; however, a software for the syllable division of Tibetan speech is still absent. Through extracting the time domain parameter short-time energy and short-time zero-crossing rate of Anduo Tibetan speech, the invention realizes Tibetan syllable division through a specific algorithm. The invention is used to carry out syllable division of 30 continuous Anduo Tibetan speech samples, and the division accuracy reaches to 30.6 percent.

Description

Technical field [0001] The method of syllable segmentation of Amdo Tibetan speech belongs to the production of Tibetan speech database and the field of Tibetan speech recognition, and is the first key technology. Background technique [0002] As we all know, language is the most convenient and fastest means for human beings to communicate and communicate with each other. It is naturally convenient, fast and efficient. With the widespread application of electronic computers and artificial intelligence, the best way of communication between humans and machines is language communication, and voice is the acoustic form of language. To make the machine understand people's speech and speak out, a lot of work needs to be done, which is speech synthesis and speech recognition technology. In the highly developed information society, it is one of the most important and basic components of the entire digital communication network to use digital methods for voice transmission, storage,...

Images