Gender-dependent acoustic models fusion developed for automatic subtitling of Parliament meetings broadcasted by the Czech TV

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F10%3A00504223" target="_blank" >RIV/49777513:23520/10:00504223 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Gender-dependent acoustic models fusion developed for automatic subtitling of Parliament meetings broadcasted by the Czech TV

Popis výsledku v původním jazyce

Gender-dependent (male/female) acoustic models are more acoustically homogeneous and therefore give better recognition performance than single gender-independent model. This paper deals with a problem how to use these gender-based acoustic models in a real-time LVCSR (Large Vocabulary Continuous Speech Recognition) system that is for more than one year used by the Czech TV for automatic subtitling of Parliament meetings that are broadcasted on the channel v{C}T24. Frequent changes of speakers and the direct connection of the LVCSR system to the TV audio stream require switching/fusion of models automatically and as soon as possible. The paper presents various techniques based on using the output probabilities for quick selection of a better model or their combinations. The best proposed method achieved over 11% relative WER reduction in comparision with the GI model.

Název v anglickém jazyce

Gender-dependent acoustic models fusion developed for automatic subtitling of Parliament meetings broadcasted by the Czech TV

Popis výsledku anglicky

Gender-dependent (male/female) acoustic models are more acoustically homogeneous and therefore give better recognition performance than single gender-independent model. This paper deals with a problem how to use these gender-based acoustic models in a real-time LVCSR (Large Vocabulary Continuous Speech Recognition) system that is for more than one year used by the Czech TV for automatic subtitling of Parliament meetings that are broadcasted on the channel v{C}T24. Frequent changes of speakers and the direct connection of the LVCSR system to the TV audio stream require switching/fusion of models automatically and as soon as possible. The paper presents various techniques based on using the output probabilities for quick selection of a better model or their combinations. The best proposed method achieved over 11% relative WER reduction in comparision with the GI model.

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2010

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

2010

Číslo periodika v rámci svazku

6231

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

8

Strana od-do

—

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—