Respeaking 3200-M1-RES-D

The aim of the course is to familiarize students with live subtitling, one of the sub-disciplines of Audiovisual Translation, and respeaking, the leading method used to create live subtitles.

Respeaking is a method based on using speech-to-text technology. A respeaker listens to original live speech and interprets it into another language or re-speaks the words he or she has heard, adding necessary punctuation and elements for the Deaf and Hard of Hearing audience (colors, labels identifying speakers) and makes the necessary editng changes. Then the words of the respeaker are processed by a speech recognition software that turns the recognized speech into text which is then displayed in the form of subtitles on a screen with as short a delay as possible.

Respeaking can be used intralingually or interlingually (to translate between languages). The target audience for live subtitles created through respeaking are the Deaf and Hard of Hearing, as well as language learners, foreigners and others. Live subtitles can be made during meetings, conferences, or as part of a live TV or internet broadcast (examples: https://www.youtube.com/watch?v=azDf-AraSPA , https://www.youtube.com/watch?v=DDMhQiakhtY , https://www.youtube.com/watch?v=xAljPi7rM-Y )
Respeakers need to master linguistic competences (the ability to simultaneously listen and speak in the same language, or to interpret live speech into a foreign language, and to paraphrase the message and make the necessary changes) and listening skills i.e. listening simultaneously their own voice as well as the original speaker so as to control one's voice and intonation and eliminate errors in speech production) and technical competences (knowledge of speech recognition tools, ability to produce subtitles, including live subtitles) and knowledge of the field of accessibility.

During the course students learn theoretical and practical issues related to live subtitling (types of live subtitles and their display methods, methods of creating live subtitles), speech recognition (types of speech recognition systems, working with the system, creating voice profiles, expanding and revising vocabulary, creating templates and macros), interlingual respeaking in Polish and interlingual respeaking from English into Polish and from Polish into English (focus and analysis, condensation and re-formulation of the text, adding punctuation and speaker IDs, , self-correcting errors and working in a team with the corrector), as well as accessibility for people with disabilities. The course covers the basics of using one's voice as a tool: choosing the microphone, adjusting pronunciation, speech pace and intonation to aid speech recognition system, creating easy to read text, as well as the use of speech recognition and respeaking skills to create prerecorded subtitles and dictates translations in CAT tools.

The final part of the course will be devoted to quality assesment in live subtitling (NER and NERT models).

The course takes place in a computer lab with professional live subtitling software and various speech recognition systems.

Type of course

elective courses

Mode

Classroom

Prerequisites (description)

Students enrolling at the course must: 1) have Polish as their mother tongue or speak Polish at (near-) native level 2) speak fluent English: - students of the Institute of Applied Linguistics must have English as their B or C language 3) students studying at the University of Warsaw as part of MOST exchange programme who study English philology/English studies or applied linguistics in English at their home universities Due to its interdisciplinary character, the course is recommended for students who fulfill one or more of the following criteria: - have completed the course "Audiovisual translation: subtitling" or similar and/or have basic knowledge of audiovisual translation; - have completed the course "Theory of interpreting" or similar and/or have basic knowledge of interpreting; - participate in courses "Consecutive interpreting" and "Simultanous interpreting" - have practical experience of interpreting and/or subtitling - have basic knowledge of media accessibility

Course coordinators

Gabriela Flis

Learning outcomes

KNOWLEDGE:
After completing the course, the student knows different methods used to create live subtitles and is familiar with professional live subtitling standards. The student also understands technical aspects and limitations related to live subtitling and their influence on the translation process.
The student knows various speech recognition systems and their limitations.
The student knows the basic rules of how to create an easy to read text.
The student understand the role of live subtitling within wider scope of accessibility for persons with disabilities.
The student knows quality assesment models NER and NERT.

SKILLS:
The student can create intralingual live subtitling in Polish and interlingual live subtilting (from English into Polish). The student can also prepare intra- and interlingual live subtitling for the deaf and hard of hearing.
The student is able to choose the most appropriate speech recognition system depending on the possibilities, needs and the topic of the event or live audiovisual show which is to be subtitled live.
The student can predict terminological issues and can preprare for them in advance by adapting the system dictionary, using templates or macros.
The student is able to identify errors in live subtitling, differentiates between recognition, edition and translation errors and is able to weigh their importance taking into account the effect on the audience. The student is able to perform quality analysis using NER and NERT models.

SOCIAL COMPETENCES:
The student knows different types of target groups using live subtitles and understands their needs.
The student understand which types of errors in live subtitling have the greatest effect on the audience.
The student is able to educate the audience and other stakeholders on the benefits of live subtitling as well as certain limitations and technological requirements that live subtitling entails.

Assessment criteria

Continuous assessment (home assignments, attendance, active participation and preparation) (50%)
Final test or semester project (50%)

Bibliography

Course textbook:

Romero-Fresco, P. (2011). Subtitling through speech recognition: Respeaking. Manchester: St. Jerome.

Reading list:

Arumi Ribas, M. and P. Romero Fresco (2008). “A practical proposal for the training of respeakers.” Journal of Specialised Translation, 10, 106-127.
Díaz Cintas, J. (2007) Audiovisual Translation: Subtitling. Manchester: St Jerome Publishing.
Eugeni, C. & Mack, A. (2008) (ed.) Intralinea, Special Issue on New Technologies in Real Time Intralingual Subtitling. http://www.intralinea.it/specials/respeaking/eng_open.php
Eugeni, C. (2008a). Respeaking the TV for the deaf: For a real special needs-oriented subtitling. Studies in English Language and Literature, 21, 37–47
Jones, R. (2002) Conference Interpreting Explained, Manchaster: St Jerome.
Jurafsky, D., & Martin, A. (2008). Speech and language processing: An introduction to natural language processing, computational linguistics, and speech recognition. New York: Prentice Hall.
Künstler, Izabela & Urszula Butkiewicz (2012) Napisy dla osób niesłyszących i słabosłyszących - zasady tworzenia. http://kulturabezbarier.org/container/Publikacja/Napisy%20dla%20nieslyszacych%20-%20zasady%20tworzenia.pdf
Lambourne, A. (2006). Subtitle respeaking: A new skill for a new age. Intralinea, 8
Media Access Australia. 2014. Caption Quality: International Approaches to Standards and Measurements. Sydney: Media Access Australia. http://www.mediaaccess.org.au/sites/default/files/files/MAA_CaptionQuality-Whitepaper.pdf
Neves, J. (2008) 10 fallacies about Subtitling for the d/Deaf and the hard of hearing. Journal of Specialised Translation. http://www.jostrans.org/issue10/art_neves.php
Ofcom. (2015). Measuring live subtitling quality: Results from the fourth sampling exercise. http://stakeholders.ofcom.org.uk/market-data-research/other/tv-research/live-subtitling/sampling_results_4/
Ofcom. 2013. Measuring the Quality of Live Subtitling: Statement. London: Ofcom. http://stakeholders.ofcom.org.uk/binaries/consultations/subtitling/statement/qos-statement.pdf.
Romero-Fresco P., Pérez J.M. (2015) “Accuracy Rate in Live Subtitling: The NER Model.” [in:] Piñero R.B., Cintas J.D. (ed.) Audiovisual Translation in a Global Context. Palgrave Studies in Translating and Interpreting. Palgrave Macmillan, London
Romero-Fresco, Pablo. 2012. Quality in live subtitling: the reception of respoken subtitles in the UK. [in:] Aline Remael, Pilar Orero and Mary Carroll (ed.) Audiovisual Translation and Media Accessibility at the Crossroads (pp. 111–31). Amsterdam: Rodopi.
Szarkowska et al. (2017) Respeaking crisis points. An exploratory study into critical moments in the respeaking process, [in:]: Deckert, M. (ed.) Audiovisual Translation – Research and Use. Bern, Switzerland: Peter Lang
Szczygielska M. (2016) Dostępne multimedia, Warszawa: Fundacja Widzialni/Ministerstwo Administracji i Cyfryzacji/Orange Polska, pp. 12-37, 47–50, 72–78, 92–125

Web resources:
International Association of Respeaking (on A.I.R., Associazione Internazionale di Respeaking)
http://www.respeakingonair.org/en/

Additional information

Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system:

Description of 3200-M1-RES-D in USOSweb