论文部分内容阅读
语音语料库是语音识别和语音合成技术研究的基础.由于维吾尔语文字与语音特征、维吾尔语语音语料库的建立、管理、使用之工作不仅工作量巨大,且具有一定的复杂性,这就不得不开发维吾尔语语音数据库管理软件.本文首先研究维吾尔语语音语料库的设计过程,包括语音文本的设计、语音录制、语音库的标注、并在此基础上论述维吾尔语语音语料管理软件的总体功能设计以及部分关键技术的实现方法.
Speech corpus is the basis of speech recognition and speech synthesis technology.Because of the Uyghur language and phonetic features, the work of establishing, managing and using Uyghur phonetic corpus is not only heavy workload, but also has certain complexity, which has to be developed Uyghur speech database management software.This paper first studies the design process of Uyghur phonetic corpus, including the design of phonetic texts, voice recordings, voice library annotation, and on the basis of the discussion of the overall functional design of Uyghur phonetic corpus management software and part The realization of key technologies.