Speaker-dependent Medium Vocabulary Continuous Speech Recognition Based on HMM and VQ

Lin Daofa; Luo Wanbo & Yang Jiayuan

您当前的位置：

首页 >

文章列表页 >

Speaker-dependent Medium Vocabulary Continuous Speech Recognition Based on HMM and VQ

更新时间：2025-12-08

- Speaker-dependent Medium Vocabulary Continuous Speech Recognition Based on HMM and VQ
- Acta Electronica Sinica Issue 7, Pages: 59-65(1992)
- 作者机构：
  
  1. 四川大学计算中心
  2. 四川大学计算中心成都 610064
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：1992
- 稿件说明：
移动端阅览
[1]林道发,罗万伯,杨家沅.基于HMM/VQ的认人的中等词表连续语音识别[J].电子学报,1992(07):59-65.

Lin Daofa, Luo Wanbo & Yang Jiayuan. Speaker-dependent Medium Vocabulary Continuous Speech Recognition Based on HMM and VQ[J]. Acta Electronica Sinica, 1992, (7): 59-65.
[1]林道发,罗万伯,杨家沅.基于HMM/VQ的认人的中等词表连续语音识别[J].电子学报,1992(07):59-65. DOI：

Lin Daofa, Luo Wanbo & Yang Jiayuan. Speaker-dependent Medium Vocabulary Continuous Speech Recognition Based on HMM and VQ[J]. Acta Electronica Sinica, 1992, (7): 59-65. DOI：

摘要

本文讨论基于隐马尔可夫模型（HMM）和矢量量化（VQ）的连续语音识别方法。用这种方法

对每个单词作成一个HMM

对多个模型组合成的状态转移网络搜索其状态转移的最佳路径

从而实现不预先进行单词切分的连续语音的识别

使用有限态文法约束及其它一些改善识别性能的措施

演示系统能识别特定人的18种英语句式

150个单词

用312个话句（共有2710个单词）进行测试

识别延迟时间为发音时长的62％

发音速度平均为每秒2.32个单词

单词识准率为97.3％。

Abstract

In this paper a method of continuous speech recognition based on hidden Markov models （HMM） and vector quantization （VQ） is discussed. According to the method

forming its own HMM for each word’s voice

searching the optimal path of state transition network combined by HMM’ s of all words of the vocabulary

it has been realized to recog-nize continuous spoken sentences without presegmentation of each word. The recognition performance is improved by using finite-state syntactic analysis and other techniques. The de-monstration system with vocabulary of 150 words can process 18 type of English sentences. The delay from speech end to getting recognition result is nearly 0.62 times as long as the duration of speech. Tested by 312 sentences including 2710 words

the word recognition accuracy is 97.3% when the average speech speed is 2.32 words per second.

关键词

Keywords

references

Views

115

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A RBF Gamma HMM Combined Model for Continuous Speech Recognition

Regionalized Decision Algorithm for Human-Machine Shared Control Based on Gaussian Hidden Markov Model

Research on Time-Serial Location Data Publication Based on Local Differential Privacy

Advance in Multiscale Geometric Analysis Image Hidden Markov Tree Model

Interpolation Adaptation Algorithm Based on Gaussian Similarity Analysis

Related Author

Li Yijun

徐近霈

吴枫

LIU Yang

SU Wei-xing

ZHU Tian-he

LIU Fang

KANG Hai-yan

Related Institution

北京大学计算机科学技术研究所栅格图象研究室!北京100871哈尔滨工业大学计算机系

哈尔滨工业大学计算机系

Department of Raster Image,Inst.of Computer Sci. & Tech.,Peking Univ.,Beijing 100871) Xu Jinpei,Wu Feng

Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems, Tiangong University

BBT-E-6 Complete Vehicle, BMW Brilliance Automotive Ltd.

⁰