Research on Tibetan Speech Recognition Based on the Am-do Dialect

作     者：Kuntharrgyal Khysru Jianguo Wei Jianwu Dang 

作者机构：Key Laboratory of Artificial Intelligence Application Technology State Ethnic Affairs CommissionQinghai Minzu UniversityXining810007China Tianjin Key Laboratory of Cognitive Computing and ApplicationTianjin UniversityTianjin300072China Japan Advanced Institute of Science and TechnologyIshikawaJapan 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第73卷第12期

页      面：4897-4907页

核心收录：

学科分类：0302[法学-政治学] 03[法学] 030204[法学-中共党史(含：党的学说与党的建设)] 

基　　金：This work was supported by the Regional Innovation Cooperation Project of Sichuan Province(Grant No.22QYCX0082) 

主　　题：Am-do dialect acoustic model language model rescoring 

摘      要：In China,Tibetan is usually divided into three major dialects:the Am-do,Khams and Lhasa *** Am-do dialect evolved from ancient Tibetan and is a local variant of modern *** this dialect has its own specific historical and social conditions and development,there have been different degrees of communication with other ethnic groups,but all the abovementioned dialects developed from the same language:*** paper uses the particularity of Tibetan suffixes in pronunciation and proposes a lexicon for the Am-do language,which optimizes the problems existing in previous *** data of the Am-do dialect are expanded by data augmentation technology combining noise and reverberation,and the morphological characteristics and characteristics of the Tibetan language are further *** to the particularity of Tibetan grammar,grammatical features are used to optimize grammatical relationships and are combined with a language model,and the Am-do dialect is scored and *** results show that compared with the baseline,our proposed new lexicon and data augmentation technology yields a relative increase of approximately 3%in character error rates(CERs)and a relative increase of 3%-19%in the recognition rate of acoustic models and language models.