Discriminative training of speaker-normalized models for automatic speech recognition
Reseach leader:Černocký Jan
Team leaders:Rath Shakti P.
Agency:JMK
Code:SIGA890
Start:2011
End:2013
Keywords:speech recognition
Annotation:
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.

Publications

2012Rath, S., P., Karafiát, M., Glembek, O., Černocký, J.: A factorized representation of FMLLR transform based on QR-decomposition, In: Proceedings of Interspeech 2012, Portland, Oregon, US, ISCA, 2012, p. 1-4, ISBN 978-1-62276-759-5, ISSN 1990-9772

Your IPv4 address: 23.22.212.158
Switch to IPv6 connection

DNSSEC [dnssec]