›› 2017, Vol. 2 ›› Issue (12): 21-26.

• 数学与计算机科学 • 上一篇    下一篇

白语语音语料库建设研究

  

  1. (1.大理大学数学与计算机学院,云南大理671003;2.大理大学学生工作处,云南大理671003)
  • 收稿日期:2017-10-11 出版日期:2017-12-15 发布日期:2017-12-15
  • 作者简介:杨健,副教授,博士,主要从事语音识别及智能信息处理研究.
  • 基金资助:
    云南省哲学社会科学规划课题(YB2017072);大理大学博士启动基金资助项目(KYBS201311)

On the Construction of a Bai Speech Corpus

  1. (1.College of Mathematics and Computer, Dali University, Dali, Yunnan 671003, China;2.Department of Student Affairs, Dali University, Dali, Yunnan 671003, China)
  • Received:2017-10-11 Online:2017-12-15 Published:2017-12-15

摘要: 白语的使用受到外来经济文化的不断冲击影响,正面临日益消亡的危险境地。针对这个问题,提出建立面向语音识别和语音合成应用的白语语音语料库,对语音语料库建设中涉及的语料采集和处理,语料库系统结构和数据存储结构,语料库用于语言学研究的接口等问题进行了阐述,提出相应的解决方法。

关键词: 白语, 语料库, 语音语料库, 语音识别

Abstract: The use of Bai language is impacted by foreign economics and cultures, which has put it in an increasingly dangerous situation of extinction. To solve this problem, this paper proposes to build a corpus for Bai speech recognition and speech synthesis application. Solutions are provided for the problems in data collection and processing, system structure and data storage structure of the corpus, and also the interface between linguistic research and the corpus.

Key words: Bai language, corpus, speech corpus, speech recognition

中图分类号: