Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
CUMANI, S. BRUMMER, J. BURGET, L. LAFACE, P. PLCHOT, O. VASILAKAKIS, V.
Originální název
Pairwise Discriminative Speaker Verification in the I -Vector Space
Typ
článek v časopise - ostatní, Jost
Jazyk
angličtina
Originální abstrakt
In this work we present a novel framework for discriminative training of speaker verification systems, where a trial is represented, as in the PLDA approach, by an i-vector pair, and the task is discrimination between same-speaker and dif- ferent-speaker classes. This pairwise SVM approach provides a more natural paradigm to speaker verification compared to the classical one-vs-all discriminative training.
Klíčová slova
Discriminative training, I-vector, large-scale training, probabilistic linear discriminant analysis, speaker recog- nition, support vector machines
Autoři
CUMANI, S.; BRUMMER, J.; BURGET, L.; LAFACE, P.; PLCHOT, O.; VASILAKAKIS, V.
Rok RIV
2013
Vydáno
20. 2. 2013
ISSN
1558-7916
Periodikum
IEEE Transactions on Audio, Speech, and Language Processing
Ročník
Číslo
6
Stát
Spojené státy americké
Strany od
1217
Strany do
1227
Strany počet
11
URL
https://ieeexplore.ieee.org/abstract/document/6466371
BibTex
@article{BUT103568, author="Sandro {Cumani} and Johan Nikolaas Langenhoven {Brummer} and Lukáš {Burget} and Pietro {Laface} and Oldřich {Plchot} and Vasileios {Vasilakakis}", title="Pairwise Discriminative Speaker Verification in the I -Vector Space", journal="IEEE Transactions on Audio, Speech, and Language Processing", year="2013", volume="2013", number="6", pages="1217--1227", doi="10.1109/TASL.2013.2245655", issn="1558-7916", url="https://ieeexplore.ieee.org/abstract/document/6466371" }