ISCSLP SR Evaluation, UVA–CS_es System Description. A System Based on ANNs

Autor:	Carlos E. Vivaracho
Rok vydání:	2006
Předmět:	Discriminative model Biometrics Channel (digital image) Artificial neural network Computer science Speech recognition Pattern recognition (psychology) Speech processing Speaker recognition Task (project management)
Zdroj:	Chinese Spoken Language Processing ISBN: 9783540496656 ISCSLP
DOI:	10.1007/11939993_55
Popis:	This paper shows a description of the system used in the ISCSLP06 Speaker Recognition Evaluation, text independent cross-channel speaker verification task. It is a discriminative Artificial Neural Network-based system, using the Non-Target Incremental Learning method to select world representatives. Two different training strategies have been followed: (i) to use world representative samples with the same channel type as the true model, (ii) to select the world representatives from a pool of samples without channel type identification. The best results have been achieved with the first alternative, but with the appearance of the additional problem of the true model channel type recognition. The system used in this task will also be shown.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::e0d9aaaac4c1d1e02aa2ef21b5fe8e62 https://doi.org/10.1007/11939993_55 Zobrazit plný text záznamu