Projekt o Rozpoznávání mluvené řeči v reálných podmínkách. Projekt navazuje na předchozí grantově podporovaný výzkum, v němž se řešitelskému týmu podařilo vyvinout a částečně i realizovat základní metody rozpoznávání řeči v českém jazyce. Aby však mohly být úspěšně nasazeny v nejvíce žádaných aplikacích, jako jsou přepisy hovorů, záznamů diskusí nebo jednání v soudních síních, musí být pozornost zaměřena na analýzu a modelování běžné mluvené (hovorové) řeči zaznamenávané v reálných podmínkách za přítomnosti šumu, hluků, případně dalších mluvících osob.

Description in English
This project follows preceding research projects within which the participating teams developed and implemented basic speech recognition algorithms for Czech. For their successful use in the most challenging applications, such as transcription of talks, recordings of court-hearings, etc., the research must continue in analysis and modelling of colloquial speech recorded in real conditions (e.g. with different backgrounds, noises, or with cross-talk). The main goal of this four-year project is to design and test new speech feature extraction techniques, background or noise suppression, speaker change-point detection, quick adaptation to new speaker characteristics, to improve lexical and phonetic inventory of recognition systems for colloquial speech, and also to develop language models with better coverage of inflective nature of Czech. This project will contribute to advancing the state-of-the-art in basic research of speech recognition and it will facilitate the integration of involved teams into European research community.

Keywords
rozpoznávání řeči

Key words in English
speech recognition

GA102/08/0707

Czech

Pollák Petr - principal person responsible
Burget Lukáš, doc. Ing., Ph.D. - fellow researcher
Černocký Jan, prof. Dr. Ing. - fellow researcher
Matějka Pavel, Ing., Ph.D. - fellow researcher
Schwarz Petr, Ing., Ph.D. - fellow researcher

Department of Computer Graphics and Multimedia
- responsible department (10.4.2008 - not assigned)
Faculty of Information Technology
- responsible department (13.5.2011 - not assigned)
Speech Data Mining Research Group BUT Speech@FIT
- internal (10.4.2008 - 31.12.2011)
Department of Computer Graphics and Multimedia
- co-beneficiary (1.1.2008 - 31.12.2011)
Faculty of Information Technology
- beneficiary (13.5.2011 - not assigned)

SCHWARZ, P. Phoneme recognition based on long temporal context. Brno: Faculty of Information Technology BUT, 2009. p. 1-95.
Detail

KARAFIÁT, M. Study of linear transformations applied to training of cross-domain adapted large vocabulary continuous speech recognition systems. Brno: 2009. p. 0-0.
Detail

DEORAS, A.; MIKOLOV, T.; KOMBRINK, S.; CHURCH, K. Approximate inference: A sampling based modeling technique to capture complex dependencies in a language model. Speech Communication, 2012, vol. 2012, no. 8, p. 1-16. ISSN: 0167-6393.
Detail

MIKOLOV, T.; KOMBRINK, S.; DEORAS, A.; BURGET, L.; ČERNOCKÝ, J. RNNLM - Recurrent Neural Network Language Modeling Toolkit. Proceedings of ASRU 2011. Hilton Waikoloa Village, Big Island, Hawaii: IEEE Signal Processing Society, 2011. p. 1-4. ISBN: 978-1-4673-0366-8.
Detail

HAIN, T.; BURGET, L.; DINES, J.; GARNER, P.; GRÉZL, F.; EL HANNANI, A.; HUIJBREGTS, M.; KARAFIÁT, M.; LINCOLN, M.; WAN, V. Transcribing Meetings with the AMIDA System. IEEE Transactions on Audio, Speech, and Language Processing, 2012, vol. 20, no. 2, p. 486-498. ISSN: 1558-7916.
Detail

KOMBRINK, S.; HANNEMANN, M.; BURGET, L. Out-of-Vocabulary Word Detection and Beyond. In Detection and Identification of Rare Audiovisual Cues. Studies in Computational Intelligence, 384. Springer-Verlag Berlin Heidelberg: Springer Verlag, 2012. p. 57-65. ISBN: 978-3-642-24033-1.
Detail

CUMANI, S.; PLCHOT, O.; KARAFIÁT, M. Independent Component Analysis and MLLR Transforms for Speaker Identification. Proc. International Conference on Acoustics, Speech, and Signal P. Kyoto: IEEE Signal Processing Society, 2012. p. 4365-4368. ISBN: 978-1-4673-0044-5.
Detail

POVEY, D.; HANNEMANN, M.; BOULIANNE, G.; BURGET, L.; GHOSHAL, A.; JANDA, M.; KARAFIÁT, M.; KOMBRINK, S.; MOTLÍČEK, P.; QIAN, Y.; RIEDHAMMER, K.; VESELÝ, K.; VU, N. Generating Exact Lattices in The WFST Framework. Proceedings of 2012 IEEE International Conference on Acoustics, Speech and Signal Processing. Kyoto: IEEE Signal Processing Society, 2012. p. 4213-4216. ISBN: 978-1-4673-0044-5.
Detail

KOMBRINK, S.; MIKOLOV, T. Recurrent Neural Network Language Modeling Applied to the Brno AMI/AMIDA 2009 Meeting Recognizer Setup. Proceedings of the 17th Conference STUDENT EEICT 2011. Volume 3. Brno: Brno University of Technology, 2011. p. 527-531. ISBN: 978-80-214-4273-3.
Detail

PEŠÁN, J. Rozpoznávání mluvčího na mobilním telefonu. Proceedings of the 17th Conference Student EEICT 2011. Volume 2. Brno: Vysoké učení technické v Brně, 2011. s. 341-343. ISBN: 978-80-214-4272-6.
Detail

GRÉZL, F.; KARAFIÁT, M.; JANDA, M. Study of Probabilistic and Bottle-Neck Features in Multilingual Environment. Proceedings of ASRU 2011. Hilton Waikoloa Village, Big Island, Hawaii: IEEE Signal Processing Society, 2011. p. 359-364. ISBN: 978-1-4673-0366-8.
Detail

MIKOLOV, T.; DEORAS, A.; POVEY, D.; BURGET, L.; ČERNOCKÝ, J. Strategies for Training Large Scale Neural Network Language Models. Proceedings of ASRU 2011. Hilton Waikoloa Village, Big Island, Hawaii: IEEE Signal Processing Society, 2011. p. 196-201. ISBN: 978-1-4673-0366-8.
Detail

BOŘIL, H.; GRÉZL, F.; HANSEN, J. Front-End Compensation Methods for LVCSR Under Lombard Effect. Proceedings of Interspeech 2011. Proceedings of Interspeech. Florence: International Speech Communication Association, 2011. p. 1257-1260. ISBN: 978-1-61839-270-1. ISSN: 1990-9772.
Detail

KOCKMANN, M.; FERRER, L.; BURGET, L.; ČERNOCKÝ, J. iVector Fusion of Prosodic and Cepstral Features for Speaker Verification. Proceedings of Interspeech 2011. Proceedings of Interspeech. Florence: International Speech Communication Association, 2011. p. 265-268. ISBN: 978-1-61839-270-1. ISSN: 1990-9772.
Detail

GRÉZL, F. The Role of Neural Network Size in TRAP/HATS Feature Extraction. Proceedings Text, Speech and Dialogue 2011. Lecture Notes in Computer Science. LNAI 6836. Plzeň: Springer Verlag, 2011. p. 315-322. ISBN: 978-3-642-23537-5. ISSN: 0302-9743.
Detail

VESELÝ, K.; KARAFIÁT, M.; GRÉZL, F. Convolutive Bottleneck Network Features for LVCSR. Proceedings of ASRU 2011. Big Island, Hawaii: IEEE Signal Processing Society, 2011. p. 42-47. ISBN: 978-1-4673-0366-8.
Detail

KARAFIÁT, M.; BURGET, L.; MATĚJKA, P.; GLEMBEK, O.; ČERNOCKÝ, J. iVector-Based Discriminative Adaptation for Automatic Speech Recognition. Proceedings of ASRU 2011. Hilton Waikoloa Village, Big Island, Hawaii: IEEE Signal Processing Society, 2011. p. 152-157. ISBN: 978-1-4673-0366-8.
Detail

KOMBRINK, S.; MIKOLOV, T.; KARAFIÁT, M.; BURGET, L. Recurrent Neural Network based Language Modeling in Meeting Recognition. Proceedings of Interspeech 2011. Proceedings of Interspeech. Florence: International Speech Communication Association, 2011. p. 2877-2880. ISBN: 978-1-61839-270-1. ISSN: 1990-9772.
Detail

MIKOLOV, T.; DEORAS, A.; KOMBRINK, S.; BURGET, L.; ČERNOCKÝ, J. Empirical Evaluation and Combination of Advanced Language Modeling Techniques. Proceedings of Interspeech 2011. Proceedings of Interspeech. Florence: International Speech Communication Association, 2011. p. 605-608. ISBN: 978-1-61839-270-1. ISSN: 1990-9772.
Detail

GRÉZL, F.; KARAFIÁT, M. Integrating recent MLP feature extraction techniques into TRAP architecture. Proceedings of Interspeech 2011. Proceedings of Interspeech. Florence: International Speech Communication Association, 2011. p. 1229-1232. ISBN: 978-1-61839-270-1. ISSN: 1990-9772.
Detail

Responsibility: Pollák Petr