{"title":"隐马尔可夫模型与矢量量化在语音独立说话人识别中的比较","authors":"D. Weber, J. du Preez","doi":"10.1109/COMSIG.1993.365856","DOIUrl":null,"url":null,"abstract":"We compare Vector Quantization and Hidden Markov Models for speaker recognition for real time recognition. A scheme to reject speakers not known to the system is described and tested. Results show that the HMM algorithm outperforms the VQ algorithm. Using a 64 state HMM, a speaker recognition accuracy of 96.1% was achieved. The rejection option generated 25.7% false rejections for a 95% confidence of a correct decision. VQ best results were 93.1% with a 61% false rejection rate for codebooks of size 128.<<ETX>>","PeriodicalId":398160,"journal":{"name":"1993 IEEE South African Symposium on Communications and Signal Processing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1993-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"A comparison between hidden Markov models and vector quantization for speech independent speaker recognition\",\"authors\":\"D. Weber, J. du Preez\",\"doi\":\"10.1109/COMSIG.1993.365856\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We compare Vector Quantization and Hidden Markov Models for speaker recognition for real time recognition. A scheme to reject speakers not known to the system is described and tested. Results show that the HMM algorithm outperforms the VQ algorithm. Using a 64 state HMM, a speaker recognition accuracy of 96.1% was achieved. The rejection option generated 25.7% false rejections for a 95% confidence of a correct decision. VQ best results were 93.1% with a 61% false rejection rate for codebooks of size 128.<<ETX>>\",\"PeriodicalId\":398160,\"journal\":{\"name\":\"1993 IEEE South African Symposium on Communications and Signal Processing\",\"volume\":\"35 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1993-08-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"1993 IEEE South African Symposium on Communications and Signal Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/COMSIG.1993.365856\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"1993 IEEE South African Symposium on Communications and Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/COMSIG.1993.365856","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A comparison between hidden Markov models and vector quantization for speech independent speaker recognition
We compare Vector Quantization and Hidden Markov Models for speaker recognition for real time recognition. A scheme to reject speakers not known to the system is described and tested. Results show that the HMM algorithm outperforms the VQ algorithm. Using a 64 state HMM, a speaker recognition accuracy of 96.1% was achieved. The rejection option generated 25.7% false rejections for a 95% confidence of a correct decision. VQ best results were 93.1% with a 61% false rejection rate for codebooks of size 128.<>
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
