越南语文本依赖的说话人识别

2013 International Conference on Soft Computing and Pattern Recognition (SoCPaR) Pub Date : 2013-12-01 DOI:10.1109/SOCPAR.2013.7054126

Diep Dao Thi Thu, Van Loan Trinh, H. Nguyen, Hung Pham Ngoc

{"title":"越南语文本依赖的说话人识别","authors":"Diep Dao Thi Thu, Van Loan Trinh, H. Nguyen, Hung Pham Ngoc","doi":"10.1109/SOCPAR.2013.7054126","DOIUrl":null,"url":null,"abstract":"This paper presents a new method for Vietnamese text-dependent speaker recognition. The system is modeled for each speaker using mixture model Gaussian GMM (Gaussian Mixture Model). The phonemes in the keywords are represented by hidden Markov models HMM. The prior and posterior probabilities for keywords and speakers have been combined together to identify speakers. The results showed that in the case the speaker did not say a long enough phrase, this approach has increased performance of speaker identification.","PeriodicalId":315126,"journal":{"name":"2013 International Conference on Soft Computing and Pattern Recognition (SoCPaR)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Text-dependent speaker recognition for vietnamese\",\"authors\":\"Diep Dao Thi Thu, Van Loan Trinh, H. Nguyen, Hung Pham Ngoc\",\"doi\":\"10.1109/SOCPAR.2013.7054126\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a new method for Vietnamese text-dependent speaker recognition. The system is modeled for each speaker using mixture model Gaussian GMM (Gaussian Mixture Model). The phonemes in the keywords are represented by hidden Markov models HMM. The prior and posterior probabilities for keywords and speakers have been combined together to identify speakers. The results showed that in the case the speaker did not say a long enough phrase, this approach has increased performance of speaker identification.\",\"PeriodicalId\":315126,\"journal\":{\"name\":\"2013 International Conference on Soft Computing and Pattern Recognition (SoCPaR)\",\"volume\":\"83 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2013 International Conference on Soft Computing and Pattern Recognition (SoCPaR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SOCPAR.2013.7054126\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 International Conference on Soft Computing and Pattern Recognition (SoCPaR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SOCPAR.2013.7054126","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 7

摘要

提出了一种基于文本的越南语说话人识别新方法。系统采用高斯混合模型(Gaussian mixture model，高斯混合模型)对每个扬声器进行建模。关键词中的音素用隐马尔可夫模型HMM表示。将关键词和说话人的先验概率和后验概率结合在一起来识别说话人。结果表明，在说话人没有说出足够长的短语的情况下，该方法提高了说话人识别的性能。

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

Text-dependent speaker recognition for vietnamese

This paper presents a new method for Vietnamese text-dependent speaker recognition. The system is modeled for each speaker using mixture model Gaussian GMM (Gaussian Mixture Model). The phonemes in the keywords are represented by hidden Markov models HMM. The prior and posterior probabilities for keywords and speakers have been combined together to identify speakers. The results showed that in the case the speaker did not say a long enough phrase, this approach has increased performance of speaker identification.

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

2013 International Conference on Soft Computing and Pattern Recognition (SoCPaR)

自引率

0.00%

发文量