Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction

机译：使用两遍决策树构造的无监督跨语言说话者自适应，用于基于HMM的语音合成

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

This paper demonstrates how unsupervised cross-lingual adaptation of HMM-based speech synthesis models may be performed without explicit knowledge of the adaptation data language. A two-pass decision tree construction technique is deployed for this purpose. Using parallel translated datasets, cross-lingual and intralingual adaptation are compared in a controlled manner. Listener evaluations reveal that the proposed method delivers performance approaching that of unsupervised intralingual adaptation.

机译：本文演示了如何在无需显式了解自适应数据语言的情况下执行基于HMM的语音合成模型的无监督跨语言自适应。为此目的，采用了两遍决策树构造技术。使用并行翻译的数据集，以受控的方式比较跨语言和跨语言的适应性。听众的评估表明，所提出的方法所提供的性能接近无监督的舌内适应。

著录项

来源
《IEEE International Conference on Acoustics Speech and Signal;ICASSP 2010》|2010年|p.4642-4645|共4页
会议地点 Dallas, TX(US);Dallas, TX(US)
作者
Gibson, Matthew; Hirsimaki, Teemu; Karhila, Reima; Kurimo, Mikko; Byrne, William;
展开▼
作者单位

Cambridge University Engineering Department Trumpington Street CB2 1PZ U.K.;

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
HMM-based speech synthesis; cross-lingual; unsupervised speaker adaptation;

机译：基于HMM的语音合成；跨语言无人监督的说话人适应;
入库时间 2022-08-26 14:40:27

相似文献

外文文献
中文文献
专利

1. Personalising speech-to-speech translation: Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis [J] . John Dines, Hui Liang, Lakshmi Saheer, Computer speech and language . 2013,第2期

机译：个性化语音到语音翻译：基于HMM的语音合成的无监督跨语言说话者自适应
2. Speaker adaptation using context clustering decision tree for HMM-based speech synthesis [J] . Junichi YAMAGISHI, Takashi MASUKO, Keiichi TOKUDA, 電子情報通信学会技術研究報告. 音声. Speech . 2003,第264期

机译：基于上下文聚类决策树的说话人自适应，用于基于HMM的语音合成
3. Speaker adaptation using context clustering decision tree for HMM-based speech synthesis [J] . Junichi YAMAGISHI, Takashi MASUKO, Keiichi TOKUDA, 電子情報通信学会技術研究報告. 音声. Speech . 2003,第264期

机译：使用上下文聚类决策树基于HMM的语音合成的扬声器适应
4. Two-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models [C] . Matthew Gibon International Speech Communication Association . 2009

机译：无监督基于HMM的合成模型的无监督改编的双通决策树构建
5. Discriminative training for speaker adaptation and minimum Bayes risk estimation in large vocabulary speech recognition. [D] . Doumpiotis, Vlasios. 2005

机译：大词汇量语音识别中的说话人适应性和最低贝叶斯风险估计的判别训练。
6. INTERACTIONS BETWEEN UNSUPERVISED LEARNING AND THE DEGREE OF SPECTRAL MISMATCH ON SHORT-TERM PERCEPTUAL ADAPTATION TO SPECTRALLY-SHIFTED SPEECH [O] . Tianhao Li, John J. Galvin III, Qian-Jie Fu -1

机译：无监督学习和光谱失配短期知觉适应对频谱移语音程度之间相互作用
7. Unsupervised intralingual and cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction [O] . Gibson Matthew, Byrne William Joseph 2010

机译：使用两遍决策树构造的基于HMM的语音合成的无监督语内和跨语说话者适应

Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction

摘要

著录项

相似文献

相关主题

期刊订阅