Expressive Multi-language Speech Synthesis Based on the Generation Process Model and Its Use for Automatic Speech Translation

基于生成过程模型的表达性多语言语音合成及其在自动语音翻译中的应用

• 批准号: 21300061
• 负责人: HIROSE Keikichi
• 金额: $ 11.23万
• 依托单位: The University of Tokyo
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B)
• 财政年份: 2009
• 资助国家: 日本
• 起止时间: 2009 至 2011
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-21300061/
• 关键词: 生成過程モデル; 基本周波数パターン; コーパスベース韻律制御; 音声自動翻訳; 談話焦点; HMM音声合成; 声質と調子; 音声モーフィング; 発話スタイル; 声調核; 多言語; 音素長; 発話焦点

A unified study on prosody control for multi-languages was conductedbased on the generation process model of fundamental frequency contours(F_0 model). We developeda method of prosody adaptation, where differences in F_0 model commands were learned from parallelspeech corpus and were applied to baseline speech. Focus control, style conversion and voiceconversion were realized. Furthermore, by approximating F_0 contours of training speech corpusand/or generated F_0 contours using the F_0 model, we improved the quality of synthetic speech by theHMM-based speech synthesis. Also, we added focus control. Based on the above results, experiments were conducted on conveying discourse information and intentions in speech Translation.

基于基频轮廓生成过程模型（F_0模型），对多语言韵律控制进行了统一研究。我们开发了一种韵律自适应方法，其中F_0模型命令的差异是从平行语音语料库中学习的，并应用于基线语音。实现了聚焦控制、风格转换和图像转换。此外，通过对训练语音库的F_0轮廓线进行逼近和/或利用F_0模型生成F_0轮廓线，我们改进了基于HMM的语音合成的质量。此外，我们还增加了焦点控制。基于以上结果，本文对言语翻译中语篇信息和意图的传递进行了实验。

项目成果

HMM-based F_0 contour synthesis using the generation process model

基于HMM的F_0轮廓合成使用生成过程模型

• 发表时间: 2012
• 期刊: Acoustical Science and Technology, Acoustical Society of Japan
• 作者: Tatsuya Matsuda;Keikichi Hirose;and Nobuaki Minematsu
• 通讯作者: and Nobuaki Minematsu

Adaptation of prosody in speech synthesis by changing command values of the generation process model of fundamental frequency

通过改变基频生成过程模型的命令值来适应语音合成中的韵律

• 发表时间: 2011
• 作者: Keikichi Hirose;Keiko Ochi;Ryusuke Mihara;Hiroya Hashimoto;Daisuke Saito;and Nobuaki Minematsu
• 通讯作者: and Nobuaki Minematsu

On the prosodic features for emotional speech

论情感言语的韵律特征

• 发表时间: 2009
• 作者: Keikichi Hirose;Qinghua Sun
• 通讯作者: Qinghua Sun

Control of prosodic features in corpus-based generation of fundamental frequency contours based on the generation process model

基于生成过程模型的基频轮廓语料库生成中韵律特征的控制

• 发表时间: 2010
• 作者: 郡山知樹;能勢隆;小林隆夫;相澤彰子;Keikichi Hirose
• 通讯作者: Keikichi Hirose

Improved generation of fundamental frequency in HMM-based speech synthesis using generation process model

使用生成过程模型改进基于 HMM 的语音合成中基频的生成

• 发表时间: 2010
• 作者: Miaomiao Wang;Miaomiao Wen;Keikichi Hirose;and Nobuaki Minematsu
• 通讯作者: and Nobuaki Minematsu