The Application of Hidden Markov Models in Speech Recognition

M. Gales, S. Young
{"title":"The Application of Hidden Markov Models in Speech Recognition","authors":"M. Gales, S. Young","doi":"10.1561/2000000004","DOIUrl":null,"url":null,"abstract":"Hidden Markov Models (HMMs) provide a simple and effective framework for modelling time-varying spectral vector sequences. As a consequence, almost all present day large vocabulary continuous speech recognition (LVCSR) systems are based on HMMs. Whereas the basic principles underlying HMM-based LVCSR are rather straightforward, the approximations and simplifying assumptions involved in a direct implementation of these principles would result in a system which has poor accuracy and unacceptable sensitivity to changes in operating environment. Thus, the practical application of HMMs in modern systems involves considerable sophistication. The aim of this review is first to present the core architecture of a HMM-based LVCSR system and then describe the various refinements which are needed to achieve state-of-the-art performance. These refinements include feature projection, improved covariance modelling, discriminative parameter estimation, adaptation and normalisation, noise compensation and multi-pass system combination. The review concludes with a case study of LVCSR for Broadcast News and Conversation transcription in order to illustrate the techniques described.","PeriodicalId":12340,"journal":{"name":"Found. Trends Signal Process.","volume":"69 1","pages":"195-304"},"PeriodicalIF":0.0000,"publicationDate":"2007-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"822","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Found. Trends Signal Process.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1561/2000000004","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 822

Abstract

Hidden Markov Models (HMMs) provide a simple and effective framework for modelling time-varying spectral vector sequences. As a consequence, almost all present day large vocabulary continuous speech recognition (LVCSR) systems are based on HMMs. Whereas the basic principles underlying HMM-based LVCSR are rather straightforward, the approximations and simplifying assumptions involved in a direct implementation of these principles would result in a system which has poor accuracy and unacceptable sensitivity to changes in operating environment. Thus, the practical application of HMMs in modern systems involves considerable sophistication. The aim of this review is first to present the core architecture of a HMM-based LVCSR system and then describe the various refinements which are needed to achieve state-of-the-art performance. These refinements include feature projection, improved covariance modelling, discriminative parameter estimation, adaptation and normalisation, noise compensation and multi-pass system combination. The review concludes with a case study of LVCSR for Broadcast News and Conversation transcription in order to illustrate the techniques described.
隐马尔可夫模型在语音识别中的应用
隐马尔可夫模型(hmm)为时变谱向量序列的建模提供了一个简单有效的框架。因此,目前几乎所有的大词汇量连续语音识别系统都是基于hmm的。然而,基于hmm的LVCSR的基本原则是相当直接的,直接实施这些原则所涉及的近似和简化假设将导致系统具有较差的准确性和对操作环境变化不可接受的敏感性。因此,hmm在现代系统中的实际应用涉及相当复杂的问题。本综述的目的是首先介绍基于hmm的LVCSR系统的核心架构,然后描述实现最先进性能所需的各种改进。这些改进包括特征投影、改进的协方差建模、判别参数估计、自适应和归一化、噪声补偿和多通道系统组合。为了说明所描述的技术,本文以LVCSR用于广播新闻和对话转录的案例研究作为总结。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信