多用途汉语方言语音数据库设计.PDFVIP

网络出版时间：2011-10-24 10:12 网络出版地址：/kcms/detail/11.2127.TP1012.045.html 2011-9-14 多用途汉语方言语音数据库的设计 ， 1 2 1 2 2 3 顾明亮 , 高原 , 孙平 , 王侠 , 张长水 1, 2 1 2 2 3 GU Ming-liang , GAO Yuan , SUN Ping , WANG Xia , ZHANG Chang-shui 1.徐州师范大学 语言科学学院,江苏 徐州 221116 2.徐州师范大学 物理与电子工程学院,江苏 徐州 221116 3.清华大学 自动化系,北京 100084 1. School of Linguistic Science, Xuzhou Normal University, Xuzhou 221116 , China 2. School of Physics and Electronic Engineering, Xuzhou Normal University, Xuzhou 221116, China 3. Department of Automation, Tsinghua University, Beijing 100084, China The Design of General-Purpose Chinese Dialect Speech Database Abstract：This paper described a general-purpose Chinese dialect speech database, which could be applied to speaker information analysis, character-words recognition, speech recognition etc. The speech database, which includes seven kinds of most commonly Chinese dialects, had reached one hundred and six hours by multi-channel record modes and had already preprocessed. Based on our work, the design criteria and implementation scheme of Chinese dialects speech database was proposed, which is useful for the establishment of Chinese speech database, especially Chinese dialect speech database. Key words：Chinese Dialect Speech Database ; Speaker Information Analysis ; Character-Words recognition 摘 要： 本文建立了一个多用途汉语方言语音数据库，用于说话人信息处理、方言特征词识别、语音识别等 领域的研究。以多通道的方式采集时长 106 小时的语音数据，包括 7 种主要的汉语方言区语音，并对数据进 行预处理。在此基础上提出了汉语方言数据库的设计标准以及实施方案，有助于推动汉语语音库特别是方言 语音