Článek ve sborníku konference

 
Santhosh, K., C., P., Li, H., Tong, R., Matějka, P., Burget, L., Černocký, J.: Tuning phone decoders for language identification, In: Proc. International Conference on Acoustics, Speech, and Signal Processing 2010, Dallas, US, IEEESP, 2010, s. 5010-5013, ISBN 978-1-4244-4296-6, ISSN 1520-6149
Jazyk publikace:angličtina
Název publikace:Tuning phone decoders for language identification
Název (cs):Ladění fonémových dekodérů pro identifikaci jazyka
Strany:5010-5013
Sborník:Proc. International Conference on Acoustics, Speech, and Signal Processing 2010
Konference:International Conference on Acoustics, Speech, and Signal Processing 2010
Místo vydání:Dallas, US
Rok:2010
ISBN:978-1-4244-4296-6
Časopis:Proc. International Conference on Acoustics, Speech, and Signal Processing, roč. 2010, č. 3, Piscataway, US
ISSN:1520-6149
Vydavatel:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2010/kumar_icassp2010_5010.pdf [PDF]
Klíčová slova
Phonotactic language identification, hidden Markov models, neural networks, mutual information, multilingual
Anotace
Článek pojednává o ladění fonémových dekodérů pro identifikaci jazyka. Studujeme, jak může být zlepšena úspěšnost systému pro identifikaci jazyka.
Abstrakt
Phonotactic approach, phone recognition to be followed by language modeling, is one of the most popular approaches to language identification (LID). In this work, we explore how language identification accuracy of a phone decoder can be enhanced by varying acoustic resolution of the phone decoder, and subsequently how multiresolution versions of the same decoder can be integrated to improve the LID accuracy. We use mutual information to select the optimum set of phones for a specific acoustic resolution. Further, we propose strategies for building multilingual systems suitable for LID applications, and subsequently fine tune these systems to enhance the overall accuracy.
BibTeX:
@INPROCEEDINGS{
   author = {Pillai Chellappan Kumar Santhosh and Haizhou Li and Rong
	Tong and Pavel Matějka and Lukáš Burget and Jan Černocký},
   title = {Tuning phone decoders for language identification},
   pages = {5010--5013},
   booktitle = {Proc. International Conference on Acoustics, Speech, and
	Signal Processing 2010},
   journal = {Proc. International Conference on Acoustics, Speech, and
	Signal Processing},
   volume = {2010},
   number = {3},
   year = {2010},
   location = {Dallas, US},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4244-4296-6},
   ISSN = {1520-6149},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9302}
}