Using Spatial Correlation Information in Speech Recognition

YU Peng; WANG Zuo-ying

您当前的位置：

首页 >

文章列表页 >

Using Spatial Correlation Information in Speech Recognition

更新时间：2025-07-16

- Using Spatial Correlation Information in Speech Recognition
- Acta Electronica Sinica Vol. 30, Issue 7, Pages: 964-966(2002)
- 作者机构：
  
  清华大学电子工程系,北京,100084
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391
- Published Online：25 July 2002，
  
  Published：2002
- 稿件说明：
移动端阅览
YU Peng, WANG Zuo-ying. Using Spatial Correlation Information in Speech Recognition[J]. Acta Electronica Sinica, 2002, 30(7): 964-966.
DOI：

YU Peng, WANG Zuo-ying. Using Spatial Correlation Information in Speech Recognition[J]. Acta Electronica Sinica, 2002, 30(7): 964-966. DOI：

摘要

在语音识别中不同语音单元的语音信号特征之间不是独立的

描述不同声学状态信号特征之间的相互关系的信息称为"空间相关性".空间相关信息在语音识别参数估计算法(训练和自适应)中有非常重要的作用.本文对这种相关性作了探讨

提出了一种在语音识别中应用空间相关信息的新方法.我们用线性方程来描述空间相关性所体现出来的不同语音单元特征之间的依赖性

通过分组K-L变换的方法来估计这组线性约束的相关系数

并给出一种结合空间相关信息的训练方法.实验结果表明

空间相关的先验知识对语音识别训练模块的稳健性有明显的提高.

Abstract

In Speech Recognition

features from different acoustic units are not independent.The correlation between different acoustic units is called "Spatial Correlation".Spatial Correlation is important for acoustic model estimation.In the paper

we proposed a new method of using spatial information in speech recognition.We use linear equation to subscribe spatial correlation

calculate equation coefficients by K-L transformation

and develop a new training algorithm with the linear constraints.Experimental results show the new method brings significant improvement in error reduction.

关键词

Keywords

references

Views

1005

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Radar Active Electromagnetic Interference Visual Detection and Parameter Estimation Method

An In-Vehicle Interaction Speech Enhancement and Recognition Method Based on Lightweight Models in Complex Environment

An End-to-End Chinese Speech Recognition Algorithm Integrating Language Model

Parameter Estimation for Logistic Model by ParticleSwarm Optimization Algorithm

Hardware Realization of Semiconductor Neurocomputer and Its Application to Continuous Speech Recognition

Related Author

ZHU Xuan

RUAN Jiang-jun

WU Hao

SHI Zhao-peng

HE Fang-min

MENG Jin

LIAN Xiao-yu

XIA Nan

Related Institution

School of Electrical Engineering and Automation, Wuhan University

National Key Laboratory of Electromagnetic Energy, Naval University of Engineering

School of Electronic Information and Communications, Huazhong University of Science and Technology

School of Information Science and Engineering， Dalian Ploytechnic University

College of Computer Science and Technology， Jilin University

⁰