Cross-Lingual Adaptation of Broadcast Transcription System to Polish Language Using Public Data Sources

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F15%3A%230003428" target="_blank" >RIV/46747885:24220/15:#0003428 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/46747885:24220/15:00002973

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Cross-Lingual Adaptation of Broadcast Transcription System to Polish Language Using Public Data Sources

Popis výsledku v původním jazyce

We present methods and procedures designed for cost-efficient adaptation of an existing speech recognition system to Polish. The system (originally built for Czech language) is adapted using common texts and speech recordings accessible from Polish web-pages. The most critical part, an acoustic model (AM) for Polish, is built in several steps, which include: a) an initial bootstrapping phase that utilizes existing Czech AM, b) a lightly-supervised iterative scheme for automatic collection and annotationof Polish speech data, and finally c) acquisition of a large amount of broadcast data in an unsupervised way. The developed system has been evaluated in the task of automatic content monitoring of major Polish TV and Radio stations. Its transcription accuracy (measured on a set of four complete TV news shows with total duration of 105 minutes) reaches almost 80 %. For clean studio speech, its accuracy gets over 92 %.

Název v anglickém jazyce

Cross-Lingual Adaptation of Broadcast Transcription System to Polish Language Using Public Data Sources

Popis výsledku anglicky

We present methods and procedures designed for cost-efficient adaptation of an existing speech recognition system to Polish. The system (originally built for Czech language) is adapted using common texts and speech recordings accessible from Polish web-pages. The most critical part, an acoustic model (AM) for Polish, is built in several steps, which include: a) an initial bootstrapping phase that utilizes existing Czech AM, b) a lightly-supervised iterative scheme for automatic collection and annotationof Polish speech data, and finally c) acquisition of a large amount of broadcast data in an unsupervised way. The developed system has been evaluated in the task of automatic content monitoring of major Polish TV and Radio stations. Its transcription accuracy (measured on a set of four complete TV news shows with total duration of 105 minutes) reaches almost 80 %. For clean studio speech, its accuracy gets over 92 %.

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

<a href="/cs/project/TA04010199" target="_blank" >TA04010199: MULTILINMEDIA - Multilinguální platforma pro monitoring a analýzu multimédií</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název statě ve sborníku

7th Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics

ISBN

978-83-932640-8-7

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

181-185

Název nakladatele

Fundancja Uniwersytetu im. Adama Mickiewicza w Poznaniu

Místo vydání

Polsko

Místo konání akce

Polsko, Poznaň

Datum konání akce

1. 1. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—