基于典型相关分析的ASR中说话人自适应频谱变换

ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing Pub Date : 1986-04-07 DOI:10.1109/ICASSP.1986.1168759

K. Choukri, G. Chollet, Y. Grenier

{"title":"基于典型相关分析的ASR中说话人自适应频谱变换","authors":"K. Choukri, G. Chollet, Y. Grenier","doi":"10.1109/ICASSP.1986.1168759","DOIUrl":null,"url":null,"abstract":"This paper describes a technique of spectral transformation for improved adaptation of a knowledge data base or reference templates to new speakers in automatic speech recognition (ASR). Based on a statistical analysis tool (Canonical correlation analysis) the proposed method permits to improve speaker independance in Large vocabulary ASR. Application to an isolated word recognizer improved a 70% correct score to 87%.","PeriodicalId":242072,"journal":{"name":"ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1986-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"28","resultStr":"{\"title\":\"Spectral transformations through canonical correlation analysis for speaker adptation in ASR\",\"authors\":\"K. Choukri, G. Chollet, Y. Grenier\",\"doi\":\"10.1109/ICASSP.1986.1168759\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper describes a technique of spectral transformation for improved adaptation of a knowledge data base or reference templates to new speakers in automatic speech recognition (ASR). Based on a statistical analysis tool (Canonical correlation analysis) the proposed method permits to improve speaker independance in Large vocabulary ASR. Application to an isolated word recognizer improved a 70% correct score to 87%.\",\"PeriodicalId\":242072,\"journal\":{\"name\":\"ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing\",\"volume\":\"6 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1986-04-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"28\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICASSP.1986.1168759\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASSP.1986.1168759","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 28

摘要

在自动语音识别(ASR)中，为了提高知识库或参考模板对新说话人的适应性，提出了一种频谱变换技术。该方法基于统计分析工具(典型相关分析)，可以提高大词汇ASR中的说话人独立性。应用于孤立词识别器将70%的正确率提高到87%。

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

Spectral transformations through canonical correlation analysis for speaker adptation in ASR

This paper describes a technique of spectral transformation for improved adaptation of a knowledge data base or reference templates to new speakers in automatic speech recognition (ASR). Based on a statistical analysis tool (Canonical correlation analysis) the proposed method permits to improve speaker independance in Large vocabulary ASR. Application to an isolated word recognizer improved a 70% correct score to 87%.

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

ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing

自引率

0.00%

发文量