CONF Adapt-ICASSP2000/IDIAP Behavior of a Bayesian adaptation method for incremental enrollment in speaker verification Fredouille, Corinne Mariéthoz, Johnny Jaboulet, Cédric Hennebert, Jean Mokbel, Chafic Bimbot, Frédéric EXTERNAL http://publications.idiap.ch/attachments/papers/2000/AdaptICASSP2000.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/adapt-icassp2000-irr2000 Related documents ICASSP2000 - IEEE International Conference on Acoustics, Speech, and Signal Processing 2000 Istanbul, Turkey IDIAP-RR 00-02 Classical adaptation approaches are generally used for speaker or environment adaptation of speech recognition systems. In this paper, we use such techniques for the incremental training of client models in a speaker verification system. The initial model is trained on a very limited amount of data and then progressively updated with access data, using a segmental-EM procedure. In supervised mode (i.e. when access utterances are certified,',','), the incremental approach yields equivalent performance to the batch one. We also investigate on the impact of various scenarios of impostor attacks during the incremental enrollment phase. All results are obtained with the Picassoft platform - the state-of-the-art speaker verification system developed in the PICASSO project. REPORT Adapt-ICASSP2000-IRR2000/IDIAP Behavior of a Bayesian adaptation method for incremental enrollment in speaker verification Fredouille, Corinne Mariéthoz, Johnny Jaboulet, Cédric Hennebert, Jean Mokbel, Chafic Bimbot, Frédéric EXTERNAL http://publications.idiap.ch/attachments/papers/2000/AdaptICASSP2000_IRR02.pdf PUBLIC Idiap-RR-02-2000 2000 IDIAP Classical adaptation approaches are generally used for speaker or environment adaptation of speech recognition systems. In this paper, we use such techniques for the incremental training of client models in a speaker verification system. The initial model is trained on a very limited amount of data and then progressively updated with access data, using a segmental-EM procedure. In supervised mode (i.e. when access utterances are certified,',','), the incremental approach yields equivalent performance to the batch one. We also investigate on the impact of various scenarios of impostor attacks during the incremental enrollment phase. All results are obtained with the Picassoft platform - the state-of-the-art speaker verification system developed in the PICASSO project.