Title:	Speaker-clustered acoustic models evaluated on GPU for on-line subtitling of parliament meetings
Authors:	Psutka, Josef V. Vaněk, Jan Psutka, Josef
Citation:	PSUTKA, Josef V.; VANĚK, Jan; PSUTKA, Josef. Speaker-clustered acoustic models evaluated on GPU for on-line subtitling of parliament meetings. In: Text, speech and dialogue. Berlin: Springer, 2011, p. 284-290. (Lectures notes in computer science; 6836). ISBN 978-3-642-23537-5.
Issue Date:	2011
Publisher:	Springer
Document type:	článek article
URI:	http://www.kky.zcu.cz/cs/publications/JosefVPsutka_2011_Speaker-clustered http://hdl.handle.net/11025/17133
ISBN:	978-3-642-23537-5
Keywords:	akustické modelování;GPU
Keywords in different language:	acoustic models;GPU
Abstract in different language:	This paper describes the effort with building speaker-clustered acoustic models as a part of the real-time LVCSR system that is used more than one year by the Czech TV for automatic subtitling of parliament meetings broadcasted on the channel ČT24. Speaker-clustered acoustic models are more acoustically homogeneous and therefore give better recognition performance than single gender-independent model or even gender-dependent models. Frequent changes of speakers and a direct connection of the LVCSR system to the audio channel require an automatic switching/fusion of models as quickly as possible. An important part of the solution is real time likelihood evaluations of all clustered acoustic models, taking advantage of a fast GPU(Graphic Processing Unit). The proposed method achieved a WER reduction to the baseline gender-independent model over 2.34% relatively with more than 2M Gaussian mixtures evaluated in real-time.
Rights:	© Josef V. Psutka - Jan Vaněk - Josef Psutka
Appears in Collections:	Články / Articles (KIV) Články / Articles (KKY)

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.