Fourth European Conference on Speech Communication and Technology

Madrid, Spain
September 18-21, 1995

Speaker Recognition Experiments on the NTIMIT Database

J.-L. Le Floch, C. Montacie, M.-J. Caraty

LAFORIA-IBP, Université Paris 6, CNRS-URA, Paris, France

In this paper, we compare three speaker recognition systems results (i.e. GMM, AHSM, ARVM) on the TIMIT and NTIMIT databases. In order to improve the results on the NTIMIT database, we present two more sophisticated systems: the first one is based on ARMA-Vector model, the second one is based on the utilisation of several AR-Vector models per speaker. We investigate the ability to recognize speaker using phonetic segments labels. We test the cooperation of several AR-Vector models, each one being learned on a distinct phonetic cluster. For this cooperation, we develop a segmental and an analytic approaches.

Full Paper

Bibliographic reference.  Floch, J.-L. Le / Montacie, C. / Caraty, M.-J. (1995): "Speaker recognition experiments on the NTIMIT database", In EUROSPEECH-1995, 379-382.