| P. Delacourt and C. Wellekens. Detection of speaker changes in an audio document. In Eurospeech, 1999. |
....show that this method effectively improves speaker recognition. Related Work The problems of speaker recognition and segmentation have been addressed by two fundamentally different approaches, either based on clustering or using Hidden Markov Models (HMMs) 9] uses agglomerative clustering and [4] distance based segmentation to detect the most likely speaker changes and the Bayesian Information Criterion to discard invalid changes. These methods combine reliability with reasonable cost, but at the price of non real time performance. The identification of speakers can also be done using ....
P. Delacourt and C. Wellekens. Detection of speaker changes in an audio document. In Eurospeech, 1999.
No context found.
P. Delacourt and C. Wellekens. Detection of speaker changes in an audio document. In Eurospeech, 1999.
No context found.
P. Delacourt, D. Kryze, C. J. Wellekens, "Detection of speaker changes in an audio document", Proc. EuroSpeech '99, pp.1195--1198 (1999)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC