Encoder Factorization for Capturing Dialect and Articulation Level in End-to-End Speech Synthesis

用于捕获端到端语音合成中的方言和发音水平的编码器分解

• 批准号: 19K24372
• 负责人: Cooper Erica
• 金额: $ 1.83万
• 依托单位: National Institute of Informatics
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Research Activity Start-up
• 财政年份: 2019
• 资助国家: 日本
• 起止时间: 2019-08-30 至 2021-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-19K24372/
• 关键词: Speech synthesis; Speaker modeling; Deep learning; Neural network; speech synthesis; dialect modeling; speaker similarity; transfer learning; neural networks; speaker modeling; deep learning; articulation

项目成果

Audio Samples for Multi-Speaker Tacotron

多扬声器 Tacotron 的音频样本

Public code for multi-speaker tacotron

多扬声器 tacotron 的公共代码

Audio sample page for Interspeech 2020 paper

Interspeech 2020 论文的音频样本页

Multi-speaker Tacotron Code

多扬声器 Tacotron 代码

Can speaker augmentation improve multi-speaker end-to-end TTS?

扬声器增强能否改善多扬声器端到端 TTS？

• 发表时间: 2020
• 作者: Erica Cooper;Cheng-I Lai;Yusuke Yasuda;and Junichi Yamagishi
• 通讯作者: and Junichi Yamagishi