Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
SOUFIFAR, M. BURGET, L. PLCHOT, O. CUMANI, S. ČERNOCKÝ, J.
Originální název
Regularized Subspace n-Gram Model for Phonotactic iVector Extraction
Typ
článek ve sborníku mimo WoS a Scopus
Jazyk
angličtina
Originální abstrakt
This article describes an enhanced phonotactic iVector extraction model over the n-gram counts. In the first step, a subspace n-gram model is proposed to model conditional n-gram probabilities. Modeling different 3-gram histories with separated multinomial distributions shows promising results for the long condition however, we observed model over-fitting for the short duration conditions.
Klíčová slova
Language identification, Subspace modeling, Subspace multinomial model
Autoři
SOUFIFAR, M.; BURGET, L.; PLCHOT, O.; CUMANI, S.; ČERNOCKÝ, J.
Rok RIV
2013
Vydáno
25. 8. 2013
Nakladatel
International Speech Communication Association
Místo
Lyon
ISBN
978-1-62993-443-3
Kniha
Proceedings of Interspeech 2013
ISSN
2308-457X
Periodikum
Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013).
Číslo
8
Stát
Francouzská republika
Strany od
74
Strany do
78
Strany počet
5
URL
http://www.fit.vutbr.cz/research/groups/speech/publi/2013/soufifar_interspeech2013_IS131171.pdf
BibTex
@inproceedings{BUT103567, author="Mehdi Mohammad {Soufifar} and Lukáš {Burget} and Oldřich {Plchot} and Sandro {Cumani} and Jan {Černocký}", title="Regularized Subspace n-Gram Model for Phonotactic iVector Extraction", booktitle="Proceedings of Interspeech 2013", year="2013", journal="Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013).", number="8", pages="74--78", publisher="International Speech Communication Association", address="Lyon", isbn="978-1-62993-443-3", issn="2308-457X", url="http://www.fit.vutbr.cz/research/groups/speech/publi/2013/soufifar_interspeech2013_IS131171.pdf" }