prikaz prve stranice dokumenta Assessment of Selected Speech Translation Apps for en-de-hr Language Pairs
  Download
PDF 1.09 MB
master's thesis
Assessment of Selected Speech Translation Apps for en-de-hr Language Pairs
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Humanities and Social Sciences, 2021. urn:nbn:hr:142:231909
Lekić, Martina
Josip Juraj Strossmayer University of Osijek
Faculty of Humanities and Social Sciences
Department of English Language and Literature

Institutional repository: FFOS-repository

Cite this document

Lekić, M. (2021). Assessment of Selected Speech Translation Apps for en-de-hr Language Pairs (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Humanities and Social Sciences. Retrieved from https://urn.nsk.hr/urn:nbn:hr:142:231909

Lekić, Martina. "Assessment of Selected Speech Translation Apps for en-de-hr Language Pairs." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Humanities and Social Sciences, 2021. https://urn.nsk.hr/urn:nbn:hr:142:231909

Lekić, Martina. "Assessment of Selected Speech Translation Apps for en-de-hr Language Pairs." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Humanities and Social Sciences, 2021. https://urn.nsk.hr/urn:nbn:hr:142:231909

Lekić, M. (2021). 'Assessment of Selected Speech Translation Apps for en-de-hr Language Pairs', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Humanities and Social Sciences, accessed 11 July 2024, https://urn.nsk.hr/urn:nbn:hr:142:231909

Lekić M. Assessment of Selected Speech Translation Apps for en-de-hr Language Pairs [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Humanities and Social Sciences; 2021 [cited 2024 July 11] Available at: https://urn.nsk.hr/urn:nbn:hr:142:231909

M. Lekić, "Assessment of Selected Speech Translation Apps for en-de-hr Language Pairs", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Humanities and Social Sciences, Osijek, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:142:231909

Metadata
TitleAssessment of Selected Speech Translation Apps for en-de-hr Language Pairs
Title (croatian)Vrednovanje odabranih aplikacija za prevođenje govora za jezične kombinacije en-hr-de
AuthorMartina Lekić
MentorMarija Omazić (mentor)
Committee memberMarija Omazić (predsjednik povjerenstva)
Committee memberDubravka Vidaković Erdeljić (član povjerenstva)
Committee memberGoran Schmidt (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Humanities and Social Sciences
(Department of English Language and Literature)
Osijek
Defense date and country2021-07-07, Croatia
Scientific / art field,
discipline and subdiscipline		HUMANISTIC SCIENCES
Philology
Anglistics
Abstract
In our technologically advanced times, when machine translation becomes qualitatively more successful and quantitatively more productive, translation technologies gain more and more trust not only of the people in need of translation, but of interpreters and translators as well. Taking into account the numerous advantages of producing translations without human boundaries, MT is becoming a reliable solution to the challenges of a constantly rising demand in quick and cheap translations. This paper focuses on the assessment of Speech-to-Speech translation apps, which bring together all of the state-of-the-art translation technology, namely, Automatic Speech Recognition, Machine Translation and Text-to-Speech Synthesis. The aim of this paper is to encompass all measurable components of a successful translation and thereby asses the overall quality of translations of conversational language produced by the S2S translation app ILA. This multi-layered research consist of a quality assessment, light-post editing, an automated translation metrics and a comparison of machine and human produced translations. Moreover, the translation output is assessed with respect to the language pair and the situation in order to gain perspective on how they affect the translation output. The given results indicate a high quality of translations produced by the S2S translation app, showing the large potential of speech technologies. Additionally, this research is setting ground for further research in this field.
Keywords
Languageenglish
URN:NBNurn:nbn:hr:142:231909
Study programmeTitle: English Language and Literature (double major); specializations in: Teacher Training, Translation and Interpreting Studies, Philology
Course: Philology
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra engleskog jezika i književnosti (magistar/magistra engleskog jezika i književnosti)
Study programmeTitle: German Language and Literature (double major); specializations in: Teacher Training, Translation Studies
Course: Translation Studies
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra njemačkog jezika i književnosti (magistar/magistra njemačkog jezika i književnosti)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-03-05 15:04:21