首页> 外文期刊>Computer speech and language >Environment adaptation for robust speaker verification by cascading maximum likelihood linear regression and reinforced learning
【24h】

Environment adaptation for robust speaker verification by cascading maximum likelihood linear regression and reinforced learning

机译:通过级联最大似然线性回归和强化学习,实现环境适应性强的说话人验证

获取原文
获取原文并翻译 | 示例
           

摘要

In speaker verification over public telephone networks, utterances can be obtained from different types of handsets. Different handsets may introduce different degrees of distortion to the speech signals. This paper attempts to combine a handset selector with (1) handset-specific transformations, (2) reinforced learning, and (3) stochastic feature transformation to reduce the effect caused by the acoustic distortion. Specifically, during training, the clean speaker models and background models are firstly transformed by MLLR-based handset-specific transformations using a small amount of distorted speech data. Then reinforced learning is applied to adapt the transformed models to handset-dependent speaker models and handset-dependent background models using stochastically transformed speaker patterns.
机译:在通过公用电话网络进行的扬声器验证中,可以从不同类型的手机中获得说话。不同的手机可能会给语音信号带来不同程度的失真。本文尝试将手机选择器与(1)手机特定的转换,(2)增强学习和(3)随机特征转换相结合,以减少由声音失真引起的影响。具体而言,在训练过程中,首先使用少量失真的语音数据,通过基于MLLR的手机特定转换来转换干净的说话者模型和背景模型。然后,应用强化学习,以使用随机转换的说话者模式将转换后的模型改编为手机相关的说话人模型和手机相关的背景模型。

著录项

  • 来源
    《Computer speech and language》 |2007年第2期|p. 231-246|共16页
  • 作者

    K.K. Yiu; M.W. Mak; S.Y. Kung;

  • 作者单位

    Department of Electronic and Information Engineering, Center for Multimedia Signal Processing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong;

    Department of Electronic and Information Engineering, Center for Multimedia Signal Processing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong;

    Department of Electrical Engineering, Princeton University, United States;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 计算技术、计算机技术;
  • 关键词

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