• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International conference on computer and automation engineering >A Combination of Maximum Likelihood Bayesian Framework and Discriminative Linear Transforms for Speaker Adaptation
【24h】

A Combination of Maximum Likelihood Bayesian Framework and Discriminative Linear Transforms for Speaker Adaptation

机译：最大似然贝叶斯框架和判别线性变换相结合的说话人适应

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

摘要

Linear transforms are one of the most commonly used methods to speaker adaptation. In this paper, we present a combinational method of Bayesian framework and maximum likelihood linear regression as well as discriminative method for speaker adaptation. Furthermore significant gains can be obtained using discriminative training for acoustic models. Experiments on supervised adaptation on Persian data show that the combinational method outperforms both Maximum likelihood linear regression and Bayesian framework. Also the proposed method with discriminative adaptation outperforms previously proposed methods for transform estimation and discriminative training outperforms ML training.
机译：线性变换是说话人自适应的最常用方法之一。在本文中，我们提出了贝叶斯框架与最大似然线性回归的组合方法以及针对说话人适应性的判别方法。此外，使用声学模型的判别训练可以获得明显的收益。在波斯数据上进行有监督适应的实验表明，该组合方法优于最大似然线性回归和贝叶斯框架。同样，具有判别适应性的拟议方法优于先前提出的用于变换估计和判别性训练的方法优于ML训练。

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