Combined Automatic Speech Recognition and Machine Translation in Business Correspondence Domain for English-Croatian

The paper presents combined automatic speech recognition (ASR) of English and machine translation (MT) for English and Croatian and Croatian-English language pairs in the domain of business correspondence. The first part presents results of training the ASR commercial system on English data sets, en...

Full description

Permalink: http://skupni.nsk.hr/Record/ffzg.KOHA-OAI-FFZG:335211/Details
Matična publikacija: WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY - International Journal of Computer, Information, Systems and Control Engineering
Vol. 8 (2014), No. 11 ; str. 1615-1621
Glavni autori: Seljan, Sanja (-), Dunđer, Ivan (Author)
Vrsta građe: Članak
Jezik: eng
Online pristup: http://www.waset.org/journal/Computer
http://waset.org/publications/9999654/combined-automatic-speech-recognition-and-machine-translation-in-business-correspondence-domain-for-english-croatian
LEADER 02439naa a22003017i 4500
005 20150112163245.0
008 150109s2014 xx eng|d
035 |a (CROSBI)704001 
040 |a HR-ZaFF  |b hrv  |c HR-ZaFF  |e ppiak 
100 1 |a Seljan, Sanja  |9 430 
245 1 0 |a Combined Automatic Speech Recognition and Machine Translation in Business Correspondence Domain for English-Croatian /  |c Seljan, Sanja ; Dunđer, Ivan. 
246 3 |i Naslov na engleskom:  |a Combined Automatic Speech Recognition and Machine Translation in Business Correspondence Domain for English-Croatian 
300 |a 1615-1621  |f str. 
363 |a Vol. 8  |b No. 11  |i 2014 
500 |a MZOS, potpora 1 - Sveučilište u Zagreb 
520 |a The paper presents combined automatic speech recognition (ASR) of English and machine translation (MT) for English and Croatian and Croatian-English language pairs in the domain of business correspondence. The first part presents results of training the ASR commercial system on English data sets, enriched by error analysis. The second part presents results of machine translation performed by free online tool for English and Croatian and Croatian- English language pairs. Human evaluation in terms of usability is conducted and internal consistency calculated by Cronbach's alpha coefficient, enriched by error analysis. Automatic evaluation is performed by WER (Word Error Rate) and PER (Position-independent word Error Rate) metrics, followed by investigation of Pearson’s correlation with human evaluation. 
536 |a Projekt MZOS  |f 3.5.1.5 
536 |a Projekt MZOS  |f 130-1300646-0909 
546 |a ENG 
690 |a 5.04 
693 |a automatic machine translation, integrated language technologies, quality evaluation, speech recognition  |l hrv  |2 crosbi 
693 |a automatic machine translation, integrated language technologies, quality evaluation, speech recognition  |l eng  |2 crosbi 
773 0 |t WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY - International Journal of Computer, Information, Systems and Control Engineering  |x 2010-3778  |g Vol. 8 (2014), No. 11 ; str. 1615-1621 
700 1 |9 1065  |a Dunđer, Ivan  |4 aut 
856 |u http://www.waset.org/journal/Computer 
856 |u http://waset.org/publications/9999654/combined-automatic-speech-recognition-and-machine-translation-in-business-correspondence-domain-for-english-croatian 
942 |c CLA  |t 1.01  |u 2  |z Znanstveni - clanak 
999 |c 335211  |d 335208