首页> 外文会议>2012 International Conference on Speech Database and Assessments. >Annotating conversational speech for corpus-based dialogue speech synthesizer — A first step
【24h】

Annotating conversational speech for corpus-based dialogue speech synthesizer — A first step

机译:为基于语料库的对话语音合成器注释对话语音-第一步

获取原文
获取原文并翻译 | 示例

摘要

This paper describes an HMM-based speech synthesis that allows dimensional description of emotion as inputs. A spontaneous dialogue speech corpus that was designed for studying paralinguistic phenomena in expressive social interactions was used to train the models, utilizing its emotional state description as additional contextual factors. In the perceptual experiment, a very high correlation was observed (R ≃ 0.8) between given pleasantness/arousal values and averaged subjective evaluations, which means that the synthesized utterances could successfully convey specified paralinguistic information.
机译:本文介绍了一种基于HMM的语音合成,该语音合成允许将维度作为输入来描述情感。设计用于研究表达性社会互动中的副语言现象的自发对话语音语料库,用于训练模型,并利用其情感状态描述作为其他上下文因素。在知觉实验中,观察到给定的愉悦度/声调值与平均主观评价之间有很高的相关性(R≃0.8),这意味着合成的话语可以成功地传达特定的副语言信息。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号