首页> 外国专利> Method for recognizing speech with noise-dependent variance normalization

Method for recognizing speech with noise-dependent variance normalization

机译:噪声相关方差归一化的语音识别方法

摘要

As the application of a variance normalization (VN) to a speech signal (S) may be advantageous as well as disadvantageous with respect to the recognition rate in a speech recognizing process in dependence of the degree of the signal disturbance it is suggested to calculate a degree (ND) of variance normalization strength in dependence of the noise level of the signal, thereby skipping the step of variance normalization in the case of an undisturbed or clean signal.
机译:由于将方差归一化(VN)应用于语音信号(S)在语音识别过程中根据信号干扰程度的识别率可能既有利又不利,因此建议计算取决于信号噪声电平的方差归一化强度(ND),从而在未受干扰或干净信号的情况下跳过方差归一化步骤。

著录项

  • 公开/公告号US7292974B2

    专利类型

  • 公开/公告日2007-11-06

    原文格式PDF

  • 申请/专利权人 THOMAS KEMP;

    申请/专利号US20020066993

  • 发明设计人 THOMAS KEMP;

    申请日2002-02-04

  • 分类号G10L15/00;

  • 国家 US

  • 入库时间 2022-08-21 21:01:03

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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