• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Speech Communication Association >Two-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models
【24h】

Two-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models

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

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Hidden Markov model (HMM) -based speech synthesis systems possess several advantages over concatenative synthesis systems. One such advantage is the relative ease with which HMM-based systems are adapted to speakers not present in the training dataset. Speaker adaptation methods used in the field of HMM-based automatic speech recognition (ASR) are adopted for this task. In the case of unsupervised speaker adaptation, previous work has used a supplementary set of acoustic models to firstly estimate the transcription of the adaptation data. By defining a mapping between HMM-based synthesis models and ASR-style models, this paper introduces an approach to the unsupervised speaker adaptation task for HMM-based speech synthesis models which avoids the need for supplementary acoustic models. Further, this enables unsupervised adaptation of HMMbased speech synthesis models without the need to perform linguistic analysis of the estimated transcription of the adaptation data.
机译：隐藏的马尔可夫模型（HMM）的基于代理合成系统具有与连接合成系统的几个优点。一个这样的优点是基于HMM的系统适用于训练数据集中不存在的扬声器的相对容易性。采用了在基于HMM的自动语音识别（ASR）字段中使用的扬声器适配方法。在扬声器适应无监督的情况下，之前的工作已经使用了一组补充声学模型来首先估计适应数据的转录。通过定义基于HMM的合成模型和ASR式模型之间的映射，本文介绍了一种基于HMM的语音合成模型的无监督者适应任务的方法，避免了对补充声学模型的需求。此外，这使得能够无监督的语音合成模型的适应性，而无需执行对适应数据的估计转录的语言分析。

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