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

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/TA01011264" target="_blank" >TA01011264: Eliminace jazykových bariér handicapovaných diváků České televize II</a><br>

Návaznosti

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

Rok uplatnění

2011

Kód důvěrnosti údajů

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

Název periodika

Lecture Notes in Computer Science

ISSN

0302-9743

e-ISSN

—

Svazek periodika

2011

Číslo periodika v rámci svazku

6836

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

7

Strana od-do

284-290

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—