摘要
This paper solves the recognition problems of the Vowel Consonant and efficiency syllable of Uighurspeech, which is based on the Center-Distance Continuance Probability Model and Uighur speech database. And it an-alyzes the result of recognition,brings forward the rationality that Uighur syllable is used as the base element ofrecognition and the difficulties we find in this study. This paper also gives the method of how to solve these problems.
This paper solves the recognition problems of the Vowel Consonant and efficiency syllable of Uighur speech, which is based on the Center-Distance Continuance Probability Model and Uighur speech database. And it analyzes the result of recognition, brings forward the rationality that Uighur syllable is used as the base element of recognition and the difficulties we find in this study. This paper also gives the method of how to solve these problem.
出处
《计算机科学》
CSCD
北大核心
2003年第7期182-184,共3页
Computer Science
基金
国家自然科学基金(项目编号:69562001)
新疆维吾尔自治区"九五"重点攻关科研项目基金(项目编号:G9532603)
关键词
语音识别
语音识别基元
维吾尔语音节
维吾尔语
Speech recognition
Center-distance continuance probability model
Uighur syllable. Base element of recognition
