Přístupnostní navigace
E-application
Search Search Close
Publication detail
KARAFIÁT, M. GRÉZL, F. HANNEMANN, M. VESELÝ, K. ČERNOCKÝ, J.
Original Title
BUT BABEL System for Spontaneous Cantonese
Type
article in a collection out of WoS and Scopus
Language
English
Original Abstract
This article describes the novel things we have brought to our BABEL Cantonese system include 6-layer Stacked Bottle-Neck features and using f0 at the input of this NN. We have also investigated into robustness of SBN training (silence, normalization) and shown an efficient combination with PLP and (again!) F0 features using Region-Dependent transforms. Last by not least, a combination of RDT with another popular adaptation technique (SAT) was shown beneficial.
Keywords
speech recognition, discriminative training, bottle-neck neural networks, region-dependent transforms
Authors
KARAFIÁT, M.; GRÉZL, F.; HANNEMANN, M.; VESELÝ, K.; ČERNOCKÝ, J.
RIV year
2013
Released
25. 8. 2013
Publisher
International Speech Communication Association
Location
Lyon
ISBN
978-1-62993-443-3
Book
Proceedings of Interspeech 2013
2308-457X
Periodical
Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013).
Number
8
State
French Republic
Pages from
2589
Pages to
2593
Pages count
5
URL
http://www.fit.vutbr.cz/research/groups/speech/publi/2013/karafiat_interspeech2013_IS131522.pdf
BibTex
@inproceedings{BUT103550, author="Martin {Karafiát} and František {Grézl} and Mirko {Hannemann} and Karel {Veselý} and Jan {Černocký}", title="BUT BABEL System for Spontaneous Cantonese", booktitle="Proceedings of Interspeech 2013", year="2013", journal="Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013).", number="8", pages="2589--2593", publisher="International Speech Communication Association", address="Lyon", isbn="978-1-62993-443-3", issn="2308-457X", url="http://www.fit.vutbr.cz/research/groups/speech/publi/2013/karafiat_interspeech2013_IS131522.pdf" }