i向量在语音和音乐分类中的应用

2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) Pub Date : 2016-12-01 DOI:10.1109/ISSPIT.2016.7885999

H. Zhang, Xukui Yang, Weiqiang Zhang, Wenlin Zhang, Jia Liu

{"title":"i向量在语音和音乐分类中的应用","authors":"H. Zhang, Xukui Yang, Weiqiang Zhang, Wenlin Zhang, Jia Liu","doi":"10.1109/ISSPIT.2016.7885999","DOIUrl":null,"url":null,"abstract":"This paper proposes a speech/music classification system based on i-vector. An analysis of two classification methods, namely cosine distance score (CDS) and support vector machine (SVM) is performed. Two session compensation methods, within-class covariance normalization (WCCN) and linear discriminant analysis (LDA) are also discussed. The performance of proposed systems yields better results compared with Gaussian mixture model (GMM) method and modified low energy ratio (MLER) method.","PeriodicalId":371691,"journal":{"name":"2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"Application of i-vector in speech and music classification\",\"authors\":\"H. Zhang, Xukui Yang, Weiqiang Zhang, Wenlin Zhang, Jia Liu\",\"doi\":\"10.1109/ISSPIT.2016.7885999\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper proposes a speech/music classification system based on i-vector. An analysis of two classification methods, namely cosine distance score (CDS) and support vector machine (SVM) is performed. Two session compensation methods, within-class covariance normalization (WCCN) and linear discriminant analysis (LDA) are also discussed. The performance of proposed systems yields better results compared with Gaussian mixture model (GMM) method and modified low energy ratio (MLER) method.\",\"PeriodicalId\":371691,\"journal\":{\"name\":\"2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)\",\"volume\":\"4 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISSPIT.2016.7885999\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISSPIT.2016.7885999","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 10

摘要

提出了一种基于i向量的语音/音乐分类系统。对余弦距离评分(CDS)和支持向量机(SVM)两种分类方法进行了分析。讨论了类内协方差归一化(WCCN)和线性判别分析(LDA)两种会话补偿方法。与高斯混合模型(GMM)方法和改进的低能量比(MLER)方法相比，所提出的系统具有更好的性能。

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

Application of i-vector in speech and music classification

This paper proposes a speech/music classification system based on i-vector. An analysis of two classification methods, namely cosine distance score (CDS) and support vector machine (SVM) is performed. Two session compensation methods, within-class covariance normalization (WCCN) and linear discriminant analysis (LDA) are also discussed. The performance of proposed systems yields better results compared with Gaussian mixture model (GMM) method and modified low energy ratio (MLER) method.

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

2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)

自引率

0.00%

发文量