Controllable Emotion Transfer For End-to-End Speech Synthesis

Tao Li, Shan Yang, Liumeng Xue, Lei Xie
{"title":"Controllable Emotion Transfer For End-to-End Speech Synthesis","authors":"Tao Li, Shan Yang, Liumeng Xue, Lei Xie","doi":"10.1109/ISCSLP49672.2021.9362069","DOIUrl":null,"url":null,"abstract":"Emotion embedding space learned from references is a straight-forward approach for emotion transfer in encoder-decoder structured emotional text to speech (TTS) systems. However, the transferred emotion in the synthetic speech is not accurate and expressive enough with emotion category confusions. Moreover, it is hard to select an appropriate reference to deliver desired emotion strength. To solve these problems, we propose a novel approach based on Tacotron. First, we plug two emotion classifiers – one after the reference encoder, one after the decoder output – to enhance the emotion-discriminative ability of the emotion embedding and the predicted mel-spectrum. Second, we adopt style loss to measure the difference between the generated and reference mel-spectrum. The emotion strength in the synthetic speech can be controlled by adjusting the value of the emotion embedding as the emotion embedding can be viewed as the feature map of the mel-spectrum. Experiments on emotion transfer and strength control have shown that the synthetic speech of the proposed method is more accurate and expressive with less emotion category confusions and the control of emotion strength is more salient to listeners.","PeriodicalId":279828,"journal":{"name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"56","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISCSLP49672.2021.9362069","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 56

Abstract

Emotion embedding space learned from references is a straight-forward approach for emotion transfer in encoder-decoder structured emotional text to speech (TTS) systems. However, the transferred emotion in the synthetic speech is not accurate and expressive enough with emotion category confusions. Moreover, it is hard to select an appropriate reference to deliver desired emotion strength. To solve these problems, we propose a novel approach based on Tacotron. First, we plug two emotion classifiers – one after the reference encoder, one after the decoder output – to enhance the emotion-discriminative ability of the emotion embedding and the predicted mel-spectrum. Second, we adopt style loss to measure the difference between the generated and reference mel-spectrum. The emotion strength in the synthetic speech can be controlled by adjusting the value of the emotion embedding as the emotion embedding can be viewed as the feature map of the mel-spectrum. Experiments on emotion transfer and strength control have shown that the synthetic speech of the proposed method is more accurate and expressive with less emotion category confusions and the control of emotion strength is more salient to listeners.
端到端语音合成的可控情感转移
从参考文献中学习情感嵌入空间是一种直接的编码-解码器结构情感文本到语音(TTS)系统的情感转移方法。然而,合成语音中传递的情感不够准确,表达不够充分,存在情感范畴混淆。此外,很难选择一个合适的参考来传递期望的情感强度。为了解决这些问题,我们提出了一种基于Tacotron的新方法。首先,我们在参考编码器和解码器输出后分别插入两个情绪分类器,以增强情绪嵌入和预测梅尔谱的情绪判别能力。其次,我们采用风格损失来衡量生成的梅尔谱与参考谱之间的差异。由于情感嵌入可以看作是梅尔谱的特征映射,因此可以通过调整情感嵌入的值来控制合成语音中的情感强度。情绪转移和强度控制实验表明,该方法合成的语音更准确,表达能力更强,情绪类别混淆更少,对情绪强度的控制更明显。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信