{"title":"一个实用的,自适应的语音活动检测器扬声器验证与嘈杂的电话和麦克风数据","authors":"T. Kinnunen, Padmanabhan Rajan","doi":"10.1109/ICASSP.2013.6639066","DOIUrl":null,"url":null,"abstract":"A voice activity detector (VAD) plays a vital role in robust speaker verification, where energy VAD is most commonly used. Energy VAD works well in noise-free conditions but deteriorates in noisy conditions. One way to tackle this is to introduce speech enhancement preprocessing. We study an alternative, likelihood ratio based VAD that trains speech and nonspeech models on an utterance-by-utterance basis from mel-frequency cepstral coefficients (MFCCs). The training labels are obtained from enhanced energy VAD. As the speech and nonspeech models are re-trained for each utterance, minimum assumptions of the background noise are made. According to both VAD error analysis and speaker verification results utilizing state-of-the-art i-vector system, the proposed method outperforms energy VAD variants by a wide margin. We provide open-source implementation of the method.","PeriodicalId":183968,"journal":{"name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","volume":"164 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"109","resultStr":"{\"title\":\"A practical, self-adaptive voice activity detector for speaker verification with noisy telephone and microphone data\",\"authors\":\"T. Kinnunen, Padmanabhan Rajan\",\"doi\":\"10.1109/ICASSP.2013.6639066\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A voice activity detector (VAD) plays a vital role in robust speaker verification, where energy VAD is most commonly used. Energy VAD works well in noise-free conditions but deteriorates in noisy conditions. One way to tackle this is to introduce speech enhancement preprocessing. We study an alternative, likelihood ratio based VAD that trains speech and nonspeech models on an utterance-by-utterance basis from mel-frequency cepstral coefficients (MFCCs). The training labels are obtained from enhanced energy VAD. As the speech and nonspeech models are re-trained for each utterance, minimum assumptions of the background noise are made. According to both VAD error analysis and speaker verification results utilizing state-of-the-art i-vector system, the proposed method outperforms energy VAD variants by a wide margin. We provide open-source implementation of the method.\",\"PeriodicalId\":183968,\"journal\":{\"name\":\"2013 IEEE International Conference on Acoustics, Speech and Signal Processing\",\"volume\":\"164 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-10-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"109\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2013 IEEE International Conference on Acoustics, Speech and Signal Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICASSP.2013.6639066\",\"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 IEEE International Conference on Acoustics, Speech and Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASSP.2013.6639066","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A practical, self-adaptive voice activity detector for speaker verification with noisy telephone and microphone data
A voice activity detector (VAD) plays a vital role in robust speaker verification, where energy VAD is most commonly used. Energy VAD works well in noise-free conditions but deteriorates in noisy conditions. One way to tackle this is to introduce speech enhancement preprocessing. We study an alternative, likelihood ratio based VAD that trains speech and nonspeech models on an utterance-by-utterance basis from mel-frequency cepstral coefficients (MFCCs). The training labels are obtained from enhanced energy VAD. As the speech and nonspeech models are re-trained for each utterance, minimum assumptions of the background noise are made. According to both VAD error analysis and speaker verification results utilizing state-of-the-art i-vector system, the proposed method outperforms energy VAD variants by a wide margin. We provide open-source implementation of the method.