Databases of Expressive Speech
Databases of Expressive Speech
复制标题
表达性言语数据库
DOI：
--
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
N. Campbell
中科院分区：
文献类型：
--
作者：
N. Campbell
本文讨论了用于语音信息处理研究的语音数据库的构建，并描述了以情感语音合成为例说明的问题。它介绍了一个用于处理表达性语音的项目，并描述了数据收集技术以及随后对语音中发出的超语言和情感特征的分析。它提出了区分说话风格差异的注释指南，并认为表达性语音处理应用程序的分析重点应该放在说话者关系（本文定义）上，而不是情绪上。
This paper discusses the construction of speech databases for research into speech information processing and describes a problem illustrated by the case of emotional speech synthesis. It introduces a project for the processing of expressive speech, and describes the data collection techniques and the subsequent analysis of supra-linguistic, and emotional features signalled in the speech. It presents annotation guidelines for distinguishing speaking-style differences, and argues that the focus of analysis for expressive speech processing applications should be on the speaker relationships (defined herein), rather than on emotions.