B6082 - Technology-Assisted Interpreting I

Learning outcomes

Students know and are able to employ as independent users the main techniques and software that lie at the foundation of real-time transformation of spoken texts.

Course contents

This course appears in both the InConf and InTeCo curricula, but under different names. In particular, for InConf the course name is METODI E TECNOLOGIE AVANZATE PER L'INTERPRETAZIONE, while for InTeCo the name is TECHNOLOGY-ASSISTED INTERPRETING I.

For the InConf curriculum

The course is delivered in the first semester and focuses on the looking up of glossaries in the interpretation booth and on the development of expertise in the area of voice recognition software for the production of real-time subtitles (also known as speech-to-text interpreting - STTI).

The first part of the course focuses on the the use of tools useful to looking up terminological resources in the interpretation booth, in particular InterpretBank.

Then, in the second part, the use of speech recognition software for the production of intralingual live subtitles will be introduced. After a theoretical introduction to the production of written text from public speeches, some of the the speech recognition tools available today will be presented. Among these, the focus will be on DIT.tafono (free speaker-independent software) and Dragon Naturally Speaking (commercial speaker-dependent software).

This will be followed by practical exercises in the production of written texts from voice input using both written and audio (visual) material.

Afterwards, the techniques for real-time production of subtitles for audio-visual products will be presented (especially for deaf people).

For the InTeCo curriculum

This course includes a platform-based part and a face-to-face part, which borrows the hours from InConf's METODI E TECNOLOGIE AVANZATE PER L'INTERPRETAZIONE course. The course will be held in Italian, with educational interpreting in English.

In the face-to-face part, the use of speech recognition software for the production of intralingual live subtitles will be introduced. After a theoretical introduction to the production of written text from public speeches, some of the the speech recognition tools available today will be presented. Among these, the focus will be on DIT.tafono (free speaker-independent software) and Dragon Naturally Speaking (commercial speaker-dependent software).

This will be followed by practical exercises in the production of written texts from voice input using both written and audio (visual) material.

Afterwards, the techniques for real-time production of subtitles for audio-visual products will be presented (especially for deaf people).

Readings/Bibliography

During lessons based on theoretical aspects, the teacher will be using the following bibliographical references:

AENOR (2005) Norma UNI: 153020. Audiodescripciòn para personas con discapacidad visual. Requisitos para la audiodescripciòn y elaboraciòn de audioguías. Madrid: AENOR

Arma, Saveria (2011) "The Language of Audio Description from a Corpus-Based Perspective". Dottorato in Lingua Inglese per Scopi Speciali, Università degli Studi di Napoli Federico II, Facoltà di Scienze Politiche. Online at http://www.fedoa.unina.it/8740/1/ARMA_Saveria_23.pdf Benecke, Bernd (2004) "Audio-Description". In Meta 49 (1), pp. 78-80

Berber-Irabian, 2010. “New Technologies and Electronic Tools in Conference Interpreting” Doctoral dissertation ISG Tarragona.
Dubuc R., “Manuel pratique de terminologie”, Conseil international de la langue française

Eugeni, C. (2007). “Il rispeakeraggio televisivo per sordi: per una sottotitolazione mirata del TG”. In InTRAlinea, vol. 9
http://www.intralinea.org/archive/article/Il_rispeakeraggio_televisivo_per_sordi

Eugeni, Carlo & Mack, Gabriele (ed.). 2006. First international seminar on new technologies in real time intralingual subtitling. inTRAlinea Special Issue Respeaking. Online at http://www.intralinea.it/specials/respeaking/ita_open.php

Fantinuoli C. (2016), InterpretBank. Redefining computer-assisted interpreting tools. Proceedings of the Translating and the Computer 38 Conference in London. Geneva: Editions Tradulex, 42-52

Fantinuoli C. (2018) "The use of comparable corpora in interpreting practice and teaching". The Interpreters' Newsletter 23, 133-149

Fantinuoli C. (2019) "The technological turn in interpreting: the challenges that lie ahead". Proceedings of the conference Übersetzen und Dolmetschen 4.0. - Neue Wege im digitalen Zeitalter, 334-354

Fantinuoli C., Pisani E. (2021) "Measuring the impact of automatic speech recognition on interpreter’s performances in simultaneous interpreting", In: Empirical studies of translation and interpreting: the post-structuralist apporach, Edited by Caiwen Wang and Binghan Zheng. Routledge

Felber H., 1984. “Terminology Manual”, Infoterm-UNESCO

Kalina, S., 2010. “New Technologies in Conference Interpreting” in Lee-Jahnke & Prunc (eds.), Am Schnittpunkt von Philologie und Translationswissenschaft. Festschrift zu Ehren von Martin Forstner. Bern: Peter Lang, 79-96

Lodge, N. K. Green, N. W. and Nunn, J. P. (1994) "Audetel, Audio Described Television – the Launch of National Trials". In Proceedings International Broadcasting Convention, IEE conference 397, Amsterdam, September 1994, pp. 140-145

Ryan, Marie-Laure (2004) (ed.) Narrative Across Media: the languages of storytelling. University of Nebraska Press. Salway, Andrew and Graham, Mike (2003) "Extracting Information about Emotions in Films". In Proceedings. 11th ACM Conference on Multimedia 2003, 4th-6th Nov. 2003, pp. 299-302

Romero-Fresco, P. (2015). “Respeaking”. In F. Pöchhacker, N. Grbić, P. Mead e R. Setton (2015). 350-351

Romero-Fresco, P. e J. Martínez Pérez (2015) “Accuracy Rate in Live Subtitling: The NER Model”. In R. Baños Piñero e J. Díaz Cintas (2015). 28-50

Sandrelli, A. (2021) “Eventi dal vivo e accessibilità: Uno studio di caso sul respeaking interlinguistico”. Lingue e Linguaggi, 43, 145-168.

Teaching methods

Lessons will take the form of workshops covering theoretical aspects as well as devoting substantial space to practical exercises (looking up of glossaries in real-time with InterpretBank and production of written texts by voice recognition).

As concerns the teaching methods of this course unit, all students must attend Module 1, 2 on Health and Safety online.

Attendance is compulsory for Conference Interpreting students (at least 70% of lessons must be attended).

Assessment methods

The assessment will consist of a practical test carried out in the interpreting booth during the examination sessions.

In particular, the ability to produce a written text from an audio file of 5 minutes with DIT.tafono or Dragon NS will be tested.

The test will be assessed in marks out of thirty. Major errors (omissions or completely wrong transcriptions) will result in the subtraction of 2 points each; minor errors (transcriptions not exactly corresponding to the original, but compatible with the text) in the subtraction of 1 point each; formal errors or oversights (e.g. capitalisation) in the subtraction of 0.5 points each.

The final marks will be published a few days later through the Moodle platform.

Teaching tools

Lessons are held in the form of workshops and will be held in person. All students will be provided with the software applications required during the lessons.

Support materials (texts, slides, instructions etc.) are made available through the Moodle e-learning platform.

Links to further information

https://moodle.sslmit.unibo.it/course/view.php?id=1636

Office hours

See the website of Claudia Lecci