The proposed project deals with automatic speech recognition. It focuses on investigation of discriminative training of speaker normalized models allowing for building more accurate speech recognition systems that are more adapted to the target user. Particular attention is devoted to the application of discriminatively trained speaker adaptations in recently proposed sub-space acoustic modeling of speech.

Description in Czech
Projekt se zabývá automatickým rozpoznáváním řeči. Zaměřuje se na výzkum diskriminativního trénování modelů normalizovaných na mluvčího, které umožní vyvinout přesnější systémy pro rozpoznávání řeči s pokročilou adaptací na cílové uživatele. Zvláštní pozornost je věnována aplikaci diskriminativně trénovaným adaptacím na mluvčího v případě sub-space modelování řeči.

Keywords
speech recognition

Key words in Czech
rozpoznávání řeči

SIGA890

English

Rath Shakti Prasad - principal person responsible

Department of Computer Graphics and Multimedia
- responsible department (29.3.2011 - not assigned)
Speech Data Mining Research Group BUT Speech@FIT
- internal (29.3.2011 - 7.1.2013)
Department of Computer Graphics and Multimedia
- beneficiary (29.3.2011 - 7.1.2013)

RATH, S.; BURGET, L.; KARAFIÁT, M.; GLEMBEK, O.; ČERNOCKÝ, J. A Region-specific Feature-space Transformation for Speaker Adaptation and Singularity Analysis of Jacobian Matrix. Proceedings of Interspeeech 2013. Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013). Lyon: International Speech Communication Association, 2013. no. 8, p. 1228-1232. ISBN: 978-1-62993-443-3. ISSN: 2308-457X.
Detail

RATH, S.; KARAFIÁT, M.; GLEMBEK, O.; ČERNOCKÝ, J. A factorized representation of FMLLR transform based on QR-decomposition. Proceedings of Interspeech 2012. Proceedings of Interspeech. Portland, Oregon: International Speech Communication Association, 2012. no. 9, p. 1-4. ISBN: 978-1-62276-759-5. ISSN: 1990-9772.
Detail

RATH, S.; POVEY, D.; VESELÝ, K.; ČERNOCKÝ, J. Improved Feature Processing for Deep Neural Networks. Proceedings of Interspeech 2013. Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013). Lyon: International Speech Communication Association, 2013. no. 8, p. 109-113. ISBN: 978-1-62993-443-3. ISSN: 2308-457X.
Detail

Responsibility: Rath Shakti Prasad