Improve the Accuracy of Recognition in Web Speech Browsing Using Context Knowledge

LI Hong-lian; WANG Chun-hua; YUAN Bao-zong

您当前的位置：

首页 >

文章列表页 >

Improve the Accuracy of Recognition in Web Speech Browsing Using Context Knowledge

更新时间：2025-07-16

- Improve the Accuracy of Recognition in Web Speech Browsing Using Context Knowledge
- Acta Electronica Sinica Vol. 30, Issue 12, Pages: 1836-1839(2002)
- 作者机构：
  
  1. 北方交通大学信息科学研究所,北京,100044
  2. 北京三星通信技术研究所,北京,100081
  3. 北方交通大学信息科学研究所北京,100044
  4. 北京三星通信技术研究所北京,100081
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391
- Published：2002
- 稿件说明：
移动端阅览
LI Hong-lian, WANG Chun-hua, YUAN Bao-zong. Improve the Accuracy of Recognition in Web Speech Browsing Using Context Knowledge[J]. Acta Electronica Sinica, 2002, 30(12): 1836-1839.
DOI：

LI Hong-lian, WANG Chun-hua, YUAN Bao-zong. Improve the Accuracy of Recognition in Web Speech Browsing Using Context Knowledge[J]. Acta Electronica Sinica, 2002, 30(12): 1836-1839. DOI：

摘要

语音识别的精度不够高一直是阻碍语音技术得以广泛应用的瓶颈

在具体的应用中充分利用背景知识是解决此问题的一种有效方法.在web语音浏览中

用户的语音输入为某个有限集的元素之一

本文利用这个特点

首先定义了一种文本字符串之间的相似度

利用相似度对识别引擎的识别结果进行后处理

进而给出更准确的识别结果.实验结果表明

采用这种方法

语音识别的正确率能够达到95%以上

为真正实现语音上网提供了有力支持.

Abstract

The accuracy of speech recognition is still a bottleneck to baffle the application of speech technology.The accuracy of recognition may be improved greatly by using context knowledge efficiently.In web speech browsing

user's speech input is usually one element of a finite set.Based on these observations

this paper first defines a kind of similarity between two Chinese text strings

then processes the recognition results of engine to acquire more accurate results.Experiments show that our approach is mostly efficient:the accuracy is improved from less than 60% to more than 95%.

关键词

Keywords

references

Views

1218

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Modeling of the Uncertainty of Image Features and Their Similarity Computing Based on Vague Sets

Determination of Basic Probability Assignment Based on Interval Numbers and Its Application

Multi-directional and Multi-scale Gabor Feature Representation and Its Matching Algorithm

Robustness of Intuitionistic Fuzzy Inference Reverse Triple I Methods Based on Similarity

Related Author

LU Huan-zhang

WEN Gong-jian

ZHAO Zhu-xin

GAO Feng

KUANG Gang-yao

JIANG Yong-mei

GAO Gui

SHI Gong-tao

Related Institution

ATR Key Laboratory, School of Electronic Science and Engineering, National University of Defense Technology

Lab of Remote Sensing Information Processing,School of Electronic Science and Engineering,NUDT

School of Computer and Information Science, Southwest University

School of Electronics and Information Technology,Shanghai Jiao Tong University

School of Computer and Information ScienceSouthwest UniversityChongqing 400715China

⁰