Department of Computer Graphics and Multimedia

Discriminative training of speaker-normalized models for automatic speech recognition

Czech title:Diskriminativní trénování modelů normalizovaných na mluvčího pro automatické rozpoznávání řeči
Research leader:Rath Shakti P.
Agency:South Moravian Region - Seventh Research Framework Programme
Keywords:speech recognition
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.


2013RATH Shakti P., BURGET Lukáš, KARAFIÁT Martin, GLEMBEK Ondřej and ČERNOCKÝ Jan. A Region-specific Feature-space Transformation for Speaker Adaptation and Singularity Analysis of Jacobian Matrix. In: Proceedings of Interspeeech 2013. Lyon: International Speech Communication Association, 2013, pp. 1228-1232. ISBN 978-1-62993-443-3. ISSN 2308-457X.
 RATH Shakti P., POVEY Daniel, VESELÝ Karel and ČERNOCKÝ Jan. Improved Feature Processing for Deep Neural Networks. In: Proceedings of Interspeech 2013. Lyon: International Speech Communication Association, 2013, pp. 109-113. ISBN 978-1-62993-443-3. ISSN 2308-457X.
2012RATH Shakti P., KARAFIÁT Martin, GLEMBEK Ondřej and ČERNOCKÝ Jan. A factorized representation of FMLLR transform based on QR-decomposition. In: Proceedings of Interspeech 2012. Portland, Oregon: International Speech Communication Association, 2012, pp. 1-4. ISBN 978-1-62276-759-5. ISSN 1990-9772.

Your IPv4 address:
Switch to https

DNSSEC [dnssec]