Doc. Dr. Ing. Jan Černocký

Advancing the automatic language recognition using streamed audio media

Reseach leader:Černocký Jan
Team leaders:Kašpárek Tomáš, Matějka Pavel, Schwarz Petr
Agency:CESNET
Code:162/2005
Start:2006
End:2007
Files: 
+Type Name Title Size Modified
iconform-blade.pdf88,1 KB2006-02-20 07:57:11
iconprojekt-blade.pdf159 KB2006-02-20 07:57:04
iconrozpocet-upravy.pdf37,5 KB2006-02-20 08:18:21
^ Select all
With selected:
Keywords:speech processing, language identification, parallel computing, unsupervised acquisition of speech data, streaming
Annotation:
The projects aims at massive usage of streamed audio for a qualitative improvement of LID (automatic language identification) system accuracy. The speech processing research group at Faculty of Information Technology, Brno University of Technology (Speech@FIT) disposes of a state-of-the-art LID system based on acoustic and phonotactic modeling. For further improvement of its accuracy, it is crucial to gather huge amounts of language-specific data. In the framework of this project, such data will be collected from available streamed sources (Internet radios), on-line stored, parameterized and processed. We will develop software for training of LID models. Resulting models and algorithms will be evaluated in international evaluation campaigns organized by NIST and in cooperation with Czech law enforcement forces.

Publications

2008BURGET Lukáš, SCHWARZ Petr, MATĚJKA Pavel, HANNEMANN Mirko, RASTROW Ariya, WHITE Christopher, KHUDANPUR Sanjeev, HEŘMANSKÝ Hynek and ČERNOCKÝ Jan. Combination of strongly and weakly constrained recognizers for reliable detection of OOVs. In: Proc. International Conference on Acoustics, Speech, and Signal Processing (ICASSP). Las Vegas: IEEE Signal Processing Society, 2008, p. 4. ISBN 1-4244-1484-9.
 PLCHOT Oldřich, HUBEIKA Valiantsina, BURGET Lukáš, SCHWARZ Petr and MATĚJKA Pavel. Acquisition of Telephone Data from Radio Broadcasts with Applications to Language Recognition. In: Proc. 11th International Conference on Text, Speech and Dialogue. Berlin: Springer Verlag, 2008, pp. 477-483. ISBN 978-3-540-87390-7.
2007BURGET Lukáš, MATĚJKA Pavel, SCHWARZ Petr, GLEMBEK Ondřej and ČERNOCKÝ Jan. Analysis of feature extraction and channel compensation in GMM speaker recognition system. IEEE Transactions on Audio, Speech, and Language Processing. 2007, vol. 15, no. 7, pp. 1979-1986. ISSN 1558-7916.
 ČERNOCKÝ Jan, BURGET Lukáš, SCHWARZ Petr, MATĚJKA Pavel, KARAFIÁT Martin, GLEMBEK Ondřej, KOPECKÝ Jiří, SZŐKE Igor, FAPŠO Michal, GRÉZL František, HUBEIKA Valiantsina and OPARIN Ilya. Search in speech, language identification and speaker recognition in Speech@FIT. In: Proc. 17th International Conference Radioelektronika, 2007. Brno: Department of Radioelectronics FEEC BUT, 2007, pp. 1-6. ISBN 978-80-214-3390-8.
 ČERNOCKÝ Jan, SZŐKE Igor, FAPŠO Michal, KARAFIÁT Martin, BURGET Lukáš, KOPECKÝ Jiří, GRÉZL František, SCHWARZ Petr, GLEMBEK Ondřej, OPARIN Ilya, SMRŽ Pavel and MATĚJKA Pavel. Search in speech for public security and defense. In: Proc. IEEE Workshop on Signal Processing Applications for Public Security and Forensics, 2007 (SAFE '07). Washington D.C.: IEEE Signal Processing Society, 2007, pp. 1-7. ISBN 1-4244-1226-9.
 FAPŠO Michal. Search in speech records. In: Proc. 13th Conference STUDENT EEICT 2007. Brno: Faculty of Electrical Engineering and Communication BUT, 2007, pp. 1-3. ISBN 978-80-214-3410-3.
 GRÉZL František and ČERNOCKÝ Jan. TRAP-based Techniques for Recognition of Noisy Speech. In: Proc. 10th International Conference on Text Speech and Dialogue (TSD 2007). Berlin: Springer Verlag, 2007, pp. 270-277. ISBN 978-3-540-74627-0.
 GRÉZL František, KARAFIÁT Martin, KONTÁR Stanislav and ČERNOCKÝ Jan. Probabilistic and bottle-neck features for LVCSR of meetings. In: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2007). Hononulu: IEEE Signal Processing Society, 2007, pp. 757-760. ISBN 1-4244-0728-1.
 HUBEIKA Valiantsina, BURGET Lukáš, MATĚJKA Pavel and ČERNOCKÝ Jan. Channel Compensation for Speaker Recognition. Brno, 2007.
 HUBEIKA Valiantsina, SZŐKE Igor, BURGET Lukáš and ČERNOCKÝ Jan. Maximum Likelihood and Maximum Mutual Information Training in Gender and Age Recognition System. In: Proc. 10th International Conference on Text Speech and Dialogue (TSD 2007). Pilsen: Springer Verlag, 2007, pp. 1-6. ISBN 978-3-540-74627-0.
 MATĚJKA Pavel, BURGET Lukáš, SCHWARZ Petr, GLEMBEK Ondřej, KARAFIÁT Martin, GRÉZL František, ČERNOCKÝ Jan, VAN Leeuwen David, BRÜMMER Niko and STRASHEIM Albert. STBU system for the NIST 2006 speaker recognition evaluation. In: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2007). Honolulu: IEEE Signal Processing Society, 2007, pp. 221-224. ISBN 1-4244-0728-1.
 MIKOLOV Tomáš, OPARIN Ilya, GLEMBEK Ondřej, BURGET Lukáš, KARAFIÁT Martin and ČERNOCKÝ Jan. Použití mluvených korpusů ve vývoji systému pro rozpoznávání českých přednášek. Praha: Charles University in Prague, 2007.
 SZŐKE Igor, BURGET Lukáš and KARAFIÁT Martin. Combination of Word and Phoneme Approach for Spoken Term Detection. Brno, 2007.
2006BURGET Lukáš, MATĚJKA Pavel and ČERNOCKÝ Jan. Discriminative Training Techniques for Acoustic Language Identification. In: Proceedings of ICASSP 2006. Toulouse, 2006, pp. 209-212.
 MATĚJKA Pavel, BURGET Lukáš, SCHWARZ Petr and ČERNOCKÝ Jan. Brno University of Technology System for NIST 2005 Language Recognition Evaluation. In: Proceedings of Odyssey 2006: The Speaker and Language Recognition Workshop. San Juan, 2006, pp. 57-64. ISBN 1-4244-0472-X.
 MATĚJKA Pavel, BURGET Lukáš, SCHWARZ Petr and ČERNOCKÝ Jan. NIST 2005 Language Recognition Evaluation. In: Proceedings of NIST LRE 2005. Washington DC: National Institute of Standards and Technology, 2006, pp. 1-37.
 MATĚJKA Pavel, SCHWARZ Petr, BURGET Lukáš and ČERNOCKÝ Jan. Use of anti-models to furher improve state-of-the-art PRLM language recognition system. In: Proceedings of ICASSP 2006. Toulouse, 2006, pp. 197-200.
 SCHWARZ Petr, MATĚJKA Pavel and ČERNOCKÝ Jan. Hierarchical structures of neural networks for phoneme recognition. In: Proceedings of ICASSP 2006. Toulouse, 2006, pp. 325-328.

Your IPv4 address: 54.198.142.4
Switch to IPv6 connection

DNSSEC [dnssec]