基于时间持续函数的混合隐马尔可夫模型的汉语语音识别

ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344) Pub Date : 1998-10-12 DOI:10.1109/ICOSP.1998.770288

Lixin Bao, J. Toyama, M. Shimbo

{"title":"基于时间持续函数的混合隐马尔可夫模型的汉语语音识别","authors":"Lixin Bao, J. Toyama, M. Shimbo","doi":"10.1109/ICOSP.1998.770288","DOIUrl":null,"url":null,"abstract":"This paper proposes mixture hidden Markov models (HMM) with a time duration function to solve the recognition of Mandarin Chinese diphthongs and several words that resemble diphthongs. We propose an autoregression model to represent the dynamical relationships of observation symbols with time variance. The model can improve the weaknesses of standard HMM and nonstationary HMM.","PeriodicalId":145700,"journal":{"name":"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1998-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Mandarin phonetic recognition using mixture hidden Markov models with time duration function\",\"authors\":\"Lixin Bao, J. Toyama, M. Shimbo\",\"doi\":\"10.1109/ICOSP.1998.770288\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper proposes mixture hidden Markov models (HMM) with a time duration function to solve the recognition of Mandarin Chinese diphthongs and several words that resemble diphthongs. We propose an autoregression model to represent the dynamical relationships of observation symbols with time variance. The model can improve the weaknesses of standard HMM and nonstationary HMM.\",\"PeriodicalId\":145700,\"journal\":{\"name\":\"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)\",\"volume\":\"18 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1998-10-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICOSP.1998.770288\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICOSP.1998.770288","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

本文提出了一种带有时间持续函数的混合隐马尔可夫模型(HMM)来解决汉语双元音和几个类似双元音的词的识别问题。我们提出了一个自回归模型来表示观测符号随时间变化的动态关系。该模型可以改善标准HMM和非平稳HMM的缺点。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Mandarin phonetic recognition using mixture hidden Markov models with time duration function

This paper proposes mixture hidden Markov models (HMM) with a time duration function to solve the recognition of Mandarin Chinese diphthongs and several words that resemble diphthongs. We propose an autoregression model to represent the dynamical relationships of observation symbols with time variance. The model can improve the weaknesses of standard HMM and nonstationary HMM.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344)

自引率

0.00%

发文量