首页> 外文期刊>電子情報通信学会技術研究報告 >Unsupervised Speaker Adaptation for Speech-to-Speech Translation System
【24h】

Unsupervised Speaker Adaptation for Speech-to-Speech Translation System

机译:语音转换系统的无监督说话人适应

获取原文
获取原文并翻译 | 示例
           

摘要

In the EMIME project, we are developing a mobile device that performs per­sonalized speech-to-speech translation such that a user's spoken input in one language is used to produce spoken output in another language, while contin­uing to sound like the user's voice. We integrate two techniques, unsupervised adaptation for HMM-based TTS using a word-based large-vocabulary contin­uous speech recognizer and cross-lingual speaker adaptation for HMM-based TTS, into a single architecture. Thus, an unsupervised cross-lingual speaker adaptation system can be developed. Listening tests show very promising re­sults, demonstrating that adapted voices sound similar to the target speaker and that differences between supervised and unsupervised cross-lingual speaker adaptation are small.
机译:在EMIME项目中,我们正在开发一种执行个性化语音到语音翻译的移动设备,以使用户使用一种语言的语音输入生成另一种语言的语音输出,同时继续听起来像用户的语音。我们将两种技术集成在一起,即使用基于单词的大词汇量连续语音识别器和基于HMM的TTS的跨语言说话者自适应两种无监督的基于HMM的TTS自适应。因此,可以开发无监督的跨语言说话者自适应系统。听力测试显示出非常有希望的结果,表明适应的声音听起来与目标说话者相似,并且有监督和无监督的跨语言发言者适应之间的差异很小。

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