Antwerp 2011

Third international symposium on live subtitling with speech recognition
Exploring new avenues and new contexts:
live subtitling and other respeaking applications for (media) accessibility
Antwerp - Friday October 21 - 2011

Audiovisual translation (AVT) has always relied on technology to achieve its communicative aims and to help make audiovisual media accessible to all. The present symposium aims to investigate the evolution and possibilities of one particular interface between AVT and technology: speech recognition software and its applications in AVT. Although the focus will be on live subtitling for television, the symposium will also review related developments such as speech-to-text and text-to-speech applications in the media. A number of socio-economic factors have impacted significantly on developments in speech recognition software and its use in AVT: While our globalised world is becoming increasingly multilingual and new legislation and subtitling quotas are forcing European broadcasters to provide 100% subtitling for deaf and hard of hearing audiences, these same broadcasters are facing critical cuts in their budgets. The problems become even more exacerbated because users of different forms of AVT are demanding better quality translations rather than simply more of the same. These trends are stimulating research into different aspects of our topic. Research into software development, software training, respeaker training, error analysis at the different stages of the respeaking process, reception research, etc. are the result The symposium at Artesis University College aims to bring together specialists from academia, software development, broadcasting and the related service industry as well as consumers and those interested in recent developments in media accessibility.

Programme & Presentations

Download programme


Opening Panel: New Perspectives in media accessibility and respeaking

Andrew Lambourne, Sysmedia Ltd
Presentation: Zen and the art of respeaking (.PDF)

Gion Linder, Swiss txt
Presentation: Challenges for broadcasters (.PDF)

Pablo Romero Fresco, University of Roehampton
Presentation: Respeaking at university (.PDF)

Panel 2: New developments in broadcasting

Erik De Snerck, VRT
Presentation: Manipulating the live subtitling delay (.PDF)

Carlo Eugeni, University of Macerata
Presentation: Subtitling RAI programmes in real-time: From speaker-independent speech recognition to live editing (.PDF)
Video: Respeaking (.MOD)
Video: Live editing (.MOD)

Panel 3: New tools and smart systems for accessibility

Pilar Orero, Universitat Autonoma de Barcelona/CAIAC
In collaboration with: Jordi Óscar Lopes, Estella Oncins, Javier Serrano and Hector Delgado
Presentation: Accessibility project for Theaters using Mobile Devices (.PDF)

Margot Mieskes, European Media Laboratory GmbH Juan Martinéz, Swiss txt
Presentation: A Web-Based Editor for Audio Titling using Synthetic Speech (.PDF)

Alessandro Tescari, Pervoice SpA
Presentation: Pervoice subtitling workstation: The new frontier of TV live subtitling (.PDF)

Panel 4: Revision, error, correction and collaboration

Luuk Van Waes, University of Antwerp / Flanders Research Foundation (FWO)
Presentation: Live subtitling with speech recognition: Causes and consequences of revisions in the production process (.PDF)

Mike Wald, University of Southampton
Presentation: Collaborative correction of Speech recognition captioning errors of lecture recordings (.PDF)

Panel 5: Training and quality

Clea Tavella, Sub-ti
Presentation: Respeaking: From practice to practice through theory and training (.PDF)

Tom Wootton, Independent Media Support
Presentation: The Ivory Tower and the market place: The commercial and pedagogical requirements of subtitling quality assessment (.PDF)

Ales Prazak, University of West Bohemia
Presentation: A four-phase respeaking training system (.PDF)

Panel 6: Training and Interpreting

Jan Craenen, Artesis University College
Presentation: Live subtitling of foreign language television programmes: A qualitative analysis of a pilot project (.PDF)

Rita Geens, University College Ghent
Presentation: How to train an interpreter into a respeaker (.PDF)

Pablo Romero Fresco, University of Roehampton
Presentation: Respeaking Training Revisited (.PDF)

Veerle Haverhals
Presentation: Practical respeaker input for training (.PDF)