Sourjya Sarkar, K. S. Rao, Dipanjan Nandi, S. B. S. Kumar
{"title":"Multilingual speaker recognition on Indian languages","authors":"Sourjya Sarkar, K. S. Rao, Dipanjan Nandi, S. B. S. Kumar","doi":"10.1109/INDCON.2013.6726131","DOIUrl":null,"url":null,"abstract":"In this paper we explore the performance of multilingual speaker recognition systems developed on the IITKGP-MLILSC speech corpus. Closed-set speaker identification and speaker verification experiments are individually conducted on 13 widely spoken Indian languages. In particular, we focus on the effect of language mismatch in the speaker recognition performance of individual languages and all languages together. The standard GMM-based speaker recognition framework is used. While the average language-independent speaker identification rate is as high as 95.21%, an average equal error rate of 11.71% shows scope for further improvement in speaker verification performance.","PeriodicalId":313185,"journal":{"name":"2013 Annual IEEE India Conference (INDICON)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 Annual IEEE India Conference (INDICON)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INDCON.2013.6726131","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8
Abstract
In this paper we explore the performance of multilingual speaker recognition systems developed on the IITKGP-MLILSC speech corpus. Closed-set speaker identification and speaker verification experiments are individually conducted on 13 widely spoken Indian languages. In particular, we focus on the effect of language mismatch in the speaker recognition performance of individual languages and all languages together. The standard GMM-based speaker recognition framework is used. While the average language-independent speaker identification rate is as high as 95.21%, an average equal error rate of 11.71% shows scope for further improvement in speaker verification performance.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
