Return to search

Rozpoznávání řeči pomocí KALDI / Rozpoznávání řeči pomocí KALDI

The topic of this thesis is to implement efficient decoder for speech recognition training system ASR Kaldi (http://kaldi.sourceforge.net/). Kaldi is already deployed with decoders, but they are not convenient for dialogue systems. The main goal of this thesis to develop a real time decoder for a dialogue system, which minimize latency and optimize speed. Methods used for speeding up the decoder are not limited to multi-threading decoding or usage of GPU cards for general computations. Part of this work is devoted to training an acoustic model and also testing it in the "Vystadial" dialogue system. Powered by TCPDF (www.tcpdf.org)

Identiferoai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:335559
Date January 2014
CreatorsPlátek, Ondřej
ContributorsJurčíček, Filip, Peterek, Nino
Source SetsCzech ETDs
LanguageEnglish
Detected LanguageEnglish
Typeinfo:eu-repo/semantics/masterThesis
Rightsinfo:eu-repo/semantics/restrictedAccess

Page generated in 0.0013 seconds