Forward and Backward Hidden Markov Model with Their Applications to Continuous Speech Recognition

王仁华; 江辉

您当前的位置：

首页 >

文章列表页 >

Forward and Backward Hidden Markov Model with Their Applications to Continuous Speech Recognition

更新时间：2025-12-08

- Forward and Backward Hidden Markov Model with Their Applications to Continuous Speech Recognition
- Acta Electronica Sinica Issue 10, (1996)
- 作者机构：
  
  中国科学技术大学电子工程与信息科学系语音通信实验室
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN912.3
- Published：1996
- 稿件说明：
移动端阅览
[1]王仁华,江辉.正反向隐马尔可夫模型及其在连续语音识别中的应用[J].电子学报,1996(10):63-68.

王仁华, 江辉. Forward and Backward Hidden Markov Model with Their Applications to Continuous Speech Recognition[J]. Acta Electronica Sinica, 1996, (10).
[1]王仁华,江辉.正反向隐马尔可夫模型及其在连续语音识别中的应用[J].电子学报,1996(10):63-68. DOI：

王仁华, 江辉. Forward and Backward Hidden Markov Model with Their Applications to Continuous Speech Recognition[J]. Acta Electronica Sinica, 1996, (10). DOI：

摘要

本文针对语音信号中客观存在的正、反向依赖特性，明确提出了用条件概率的概念来定量表述语音信号的这种正、反向的马尔可大依赖关系，提出了描述语音信号这种正反向依赖关系的正反向隐马尔可夫模型（ＨＭＭ），并用实验证明了仅仅利用语音反向依赖关系语音识别同样也能获得相当可观的识别性能。接着，本文针对孤立字和连续语音两种不同的识别任务，研究了在语音识别中同时利用这两种依赖信息的方法，并提出了一种连续语音识别中的新的搜索算法──正反向分半混合搜索。这种方法利用基于正向ＨＭＭ的正向Ｖｉｔｅｒｂｉ搜索和基于反向ＨＭＭ的反向Ｖｉｔｅｒｂｉ搜索的中间结果来有效地结合正反向依赖信息，实验证明正反向分半混合搜索方法确实一致地优于单用任何一种依赖信息的单向搜索识别方法。

Abstract

In view of objectively-existing forward and backward contextual dependent information in speech signal

in this paper we show that a conditional probability can be used to explicitly express these information in speech signal

which is called Forward and Backward Markov Contextual Dependences. And the Forward and Backward Hidden Markov Models

which are believed to contain these two Markov Contextual Dependences respectively

are also presented here. Our experimental results prove that we can obtain the relatively acceptable performance in speech recognition only using the Backward Markov Contextual Dependence. It is at least comparable with the recognition performance obtained from normal forward HMM with Forward Markov Contextual Dependence. In this paper

we also study the methods of simutaneously taking advantages of these two Markov Contextual Dependences of speech in isolated word recognition and continuous speech recognition respectively

and propose an effective algorithm in continuous speech recognition-Forward and Backward Mixed Bisected Search（FBMBS）

which can utilize the immediate results of Forward HMM based forward Viterbi search and Backward HMM based backward Viterbi search

so that we can conveniently combine these two Markov Contextual Dependences in continuous speech recognition at the same time. Our experiments show that the FBMBS algorithm really is consistently superior to that of using either of these two Contextual Dependences alone.

关键词

Keywords

references

Views

234

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

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

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

Interpolation Adaptation Algorithm Based on Gaussian Similarity Analysis

Lip-Movement Features Extraction and Recognition Based on Chroma Analysis

Related Author

LIAN Xiao-yu

XIA Nan

DAI Gao-le

YANG Hong-qin

LÜ Kun-ru

WU Chun-guo

LIANG Yan-chun

YUAN Yu-ping

Related Institution

School of Information Science and Engineering， Dalian Ploytechnic University

Ministry of Education Key Laboratory of Symbol Computation and Knowledge Engineering， Jilin University

School of Computer Science， Zhuhai College of Science and Technology

College of Computer Science and Technology， Jilin University

School of InformationZhejiang University of TechnologyHangzhouZhejiang 310014China

⁰