Speaker-clustered Acoustic Models Evaluated on GPU for on-line Subtitling of Parliament Meetings

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F11%3A43898287" target="_blank" >RIV/49777513:23520/11:43898287 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1007/978-3-642-23538-2_36" target="_blank" >http://dx.doi.org/10.1007/978-3-642-23538-2_36</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-642-23538-2_36" target="_blank" >10.1007/978-3-642-23538-2_36</a>

Result language

angličtina

Original language name

Speaker-clustered Acoustic Models Evaluated on GPU for on-line Subtitling of Parliament Meetings

Original language description

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 Cˇ T24. 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.

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

<a href="/en/project/TA01011264" target="_blank" >TA01011264: Elimination of the language barriers faced by the handicapped watchers of the Czech Television II</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2011

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Lecture Notes in Computer Science

ISSN

0302-9743

e-ISSN

—

Volume of the periodical

2011

Issue of the periodical within the volume

6836

Country of publishing house

DE - GERMANY

Number of pages

7

Pages from-to

284-290

UT code for WoS article

—

EID of the result in the Scopus database

—