Skip to main content

ACCESIBILIDAD LINGUISTICA Y SENSORIAL: TECNOLOGIAS PARA LAS VOCES SUPERPUESTAS Y LA AUDIODESCRIPCION

FFI2012-31024

•
Funding agency name Ministerio de Economía y Competitividad
Funding agency acronym MINECO
Program Programa Nacional de Proyectos de Investigación Fundamental
Subprogram Subprograma de Proyectos de Investigación Fundamental no Orientada
Call Proyectos I+D
Call year 2012
State Plan 2008-2011 Plan Nacional de Investigación Científica, Desarrollo e Innovación Tecnológica
Management unit Secretaría de Estado de Investigación, Desarrollo e Innovación
Beneficiary centre UNIVERSIDAD AUTONOMA DE BARCELONA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 23
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publication Contribución de congreso (ConferenceOutput)

Enhancing sensorial and linguistic accessibility with technology, further developments in the TECNACC and ALST projects

  • Matamala, Anna|||0000-0002-1607-9011
  • Fernández Torné, Ana|||0000-0002-0132-5945
  • Ortiz-Boix, Carla
Dipòsit Digital de Documents de la UAB
Publication Contribución de congreso (ConferenceOutput)

Methodological considerations for the evaluation of TTS AD's acceptance in the Catalan context

Dipòsit Digital de Documents de la UAB
Publication Contribución de congreso (ConferenceOutput)

Tecnologies i accessibilitat

  • Matamala, Anna|||0000-0002-1607-9011
La presència de la tecnologia en l'àmbit de l'accessibilitat als continguts audiovisuals és creixent, com també les recerques que es fan sobre aquest tema. Les tecnologies es veuen com una eina que pot ajudar a incrementar l'accessibilitat a aquests continguts, si bé certes veus, especialment de professionals, s'alcen per alertar sobre els riscos que aquestes noves eines tenen per a la qualitat. En aquesta presentació volem fer un repàs d'alguns dels projectes que duem a terme al grup TransMedia Catalonia sobre tecnologies, en especial el projecte "Accessibilitat lingüística i sensorial", finançat pel Ministeri d'Economia i Competitivitat (FFI2012-31024). Abordarem la possible aplicació del reconeixement de parla, la traducció automàtica i la síntesi de parla en l'àmbit de l'accessibilitat, i descriurem els experiments que hem dut a terme en el marc d'aquest projecte. També veurem com nous suports i noves formes de consum de continguts audiovisuals com ara les segones pantalles obren possibilitats per a l'accessibilitat. Al final de la presentació farem tot un seguit de reflexions sobre l'impacte que les tecnologies tenen a diversos nivells: en el procés de creació, en la distribució i en la recepció per part dels usuaris, i també en la investigació i la formació.
Dipòsit Digital de Documents de la UAB
Publication Contribución de congreso (ConferenceOutput)

Traducción automática y síntesis de habla para la audiodescripción en castellano, un estudio exploratorio

Dipòsit Digital de Documents de la UAB
Publication Contribución de congreso (ConferenceOutput)

Estandarditzar l'audiodescripció

Dipòsit Digital de Documents de la UAB
Publication Contribución de congreso (ConferenceOutput)

Formar en accessibilitat als mitjans, noves necessitats socials, noves tecnologies, noves propostes dinàmiques

Dipòsit Digital de Documents de la UAB
Publication Contribución de congreso (ConferenceOutput)

Machine translation and audio description, is it worth it? Assessing post-editing effort

Dipòsit Digital de Documents de la UAB
Publication

MT Post-editing into the mother tongue or into a foreign language?, Spanish-to-English MT translation output post-edited by translation trainees

  • Sánchez-Gijón, Pilar|||0000-0001-5919-4629
  • Torres-Hostench, Olga|||0000-0003-1525-0304
The aim of this study is to analyse whether translation trainees who are not native speakers of the target language are able to perform as well as those who are native speakers, and whether they achieve the expected quality in a "good enough" post-editing (PE) job. In particular the study focuses on the performance of two groups of students doing PE from Spanish into English: native English speakers and native Spanish speakers. A pilot study was set up to collect evidence to compare and contrast the two groups' performances. Trainees from both groups had been given the same training in PE and were asked to post-edit 30 sentences translated from Spanish to English. The PE output was analyzed taking into account accuracy errors (mistranslations and omissions) as well as language errors (grammatical errors and syntax errors). The results show that some native Spanish speakers corrected just as many errors as the native English speakers. Furthermore, the Spanish-speaking trainees outperformed their English-speaking counterparts when identifying mistranslations and omissions. Moreover, the performances of the best English-speaking and Spanish-speaking trainees at identifying grammar and syntax errors were very similar.
Dipòsit Digital de Documents de la UAB
Publication

Audio describing characters, what features do audiences remember?

  • Fresno, Nazaret|||0000-0002-6702-159X
  • Castellà Mate, Judit|||0000-0002-6094-3516
  • Matamala, Anna|||0000-0002-1607-9011
  • Soler Vilageliu, Olga|||0000-0001-9219-1913
The audio description of characters in films encompasses from brief descriptions to long and detailed ones. Guidelines and standards suggest how to approach the audio description of characters, and some practitioners, such as Bernd Benecke, have even developed models for character audio description. However, it remains to be determined how the audience receives audio descriptions and how various strategies (inclusion of more or less features, inclusion of these features in one or more silent gaps) affect the end user reception. This paper will present part of the results of a reception study aimed at exploring whether the amount of information included in the audio description of characters and its presentation have an effect on user's recall. Testing materials included four self-contained clips in four different conditions (long/short character audio description, presentation in one block/more blocks of information). Forty-four blind or visually impaired participants (21 male, 23 female), aged 18 to 76, were asked to watch four audio clips, one per condition. Free recall and recognition questionnaires were then administered, as well as a WAIS-III Digit Span Forward test to measure participants' memory span and classify them into two groups (low/high span). Results indicate what strategies enhance character recall, but also provide data on what features are more frequently recalled by audiences and which ones are generally obviated. This specific aspect will be the focus of our presentation. The results will be discussed from two perspectives: on the one hand, taking into account how they relate to current theoretical models of character construction and, on the other, analysing how they can be transferred into real practices or recommendations.
Dipòsit Digital de Documents de la UAB
Publication Contribución de congreso (ConferenceOutput)

Speech and translation technologies for voice-over and audio description: final results of the ALST project

  • Matamala, Anna|||0000-0002-1607-9011
The ALST project (FFI-201231024, funded by the Spanish Ministry of Economy) started in January 2013 aiming to research the implementation of speech technologies (speech recognition and speech synthesis) and translation technologies (machine translation) in two audiovisual transfer modes: audio description, and voice-over. The project will end in December 2015, and the presentation will give an overview of the main objectives of the project as well as its main results. Although limited in its funding and scope, the project has carried out innovative research in the following aspects: a) Implementation of automatic speech recognition and respeaking to generate faster transcripts: experiments have been carried out with professional transcribers to compare various working scenarios (manual transcription/automatic speech recognition/respeaking). b) Implementation of machine translation plus post-editing as an alternative to traditional audiovisual translation: experiments have been carried out using audio descriptions (English into Catalan) and also wildlife documentaries to be voiced over (English into Spanish). c) Implementation of text-to-speech systems instead of human voices, both in audio descriptions and documentaries. All experiments have in common the willingness to obtain objective data (generally linked to the productivity gain in terms of time) but also subjective data on user experience and perceived quality. The presentation will not get into a detailed analysis of all experiments for obvious time constraints, but will offer a general structured overview that will allow the audience to understand the main results of the project as well as possible future research venues.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Text-to-speech vs. human voiced audio descriptions, a reception study in films dubbed into Catalan

  • Fernández Torné, Ana|||0000-0002-0132-5945
  • Matamala, Anna|||0000-0002-1607-9011
This article presents an experiment that aims to determine whether blind and visually impaired people would accept the implementation of text-to-speech in the audio description of dubbed feature films in the Catalan context. A user study was conducted with 67 blind and partially sighted people who assessed two synthetic voices when applied to audio description, as compared to two natural voices. All of the voices had been previously selected in a preliminary test. The analysis of the data (both quantitative and qualitative) concludes that most participants accept Catalan text-to-speech audio description as an alternative solution to the standard human-voiced audio description. However, natural voices obtain statistically higher scores than synthetic voices and are still the preferred solution.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

The reception of subtitled colloquial language in Catalan, en eye-tracking exploratory study

  • Fernández Torné, Ana|||0000-0002-0132-5945
  • Matamala, Anna|||0000-0002-1607-9011
  • Vilaró Soler, Anna|||0000-0001-9673-8322
Usually, colloquial oral features in audiovisual fiction disappear when the oral language is transferred into written text by means of interlingual subtitles. Expressive devices and colloquial items are often omitted for the sake of condensation; standard forms generally substitute non-standard units; and grammatical mistakes are often corrected. However, not all the agents involved in the subtitling industry tackle this issue in the same way. For instance, at the Catalan Television (TVC), there has been an internal debate concerning the use of non-standard forms in subtitles, particularly concerning colloquial pronominal clitics. Moving away from this debate, by using eyetracking technologies and questionnaires, this exploratory study aims to investigate whether using non-standard colloquial pronominal clitics instead of standard pronominal clitics alters the reception of the audiovisual product, and whether this approach is effective in transmitting the colloquial flavour of the dialogues.
Dipòsit Digital de Documents de la UAB
Publication

Quality assessment of post-edited versus translated wildlife documentary films, a three-level approach

  • Ortiz-Boix, Carla
  • Matamala, Anna|||0000-0002-1607-9011
This article presents the results of a study designed to evaluate the quality of post-edited wildlife documentary films (in comparison to translated) which are delivered using voiceover and off-screen dubbing. The study proposes a quality assessment at three levels: experts' assessment, dubbing studio's assessment and end-users' assessment. The main contribution of this quality assessment proposal is the inclusion of end-users in the process of assessing the quality of post-edited and translated audiovisual texts. Results show that there is no meaningful difference between the quality of post-edited and translated wildlife documentary films, although translations perform better in certain aspects
Dipòsit Digital de Documents de la UAB
Publication Contribución de congreso (ConferenceOutput)

The reception of intralingual and interlingual subtitling, an exploratory study within the HBB4ALL project

Dipòsit Digital de Documents de la UAB
Publication

The reception of intralingual and interlingual subtitling, an exploratory study within the HBB4ALL project

Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Post-editing wildlife documentary films, a new possible scenario?

  • Ortiz-Boix, Carla
  • Matamala, Anna|||0000-0002-1607-9011
Several studies have proven that, when machine translation followed by post-editing is used to translate general and specialised texts, there is an increase in the productivity, as the post-editing effort is lower than translating ex novo. Although the use of machine translation and post-editing has been investigated in Audiovisual Translation, this has never been researched in non-fictional audiovisual genres in which voice-over and off-screen dubbing are applied. Using an English wildlife documentary film as the source text, and Spanish as the target language, this study intends to research whether post-editing involves more or less effort than translating a documentary. Conclusions on the experiment described in this article, in which 12 Audiovisual Translation MA students took part, seem to indicate that post-editing involves less effort than translating
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Accessibility and multilingualism, an exploratory study on the machine translation of audio descriptions, Accesibilidad y multilingüismo

  • Matamala, Anna|||0000-0002-1607-9011
  • Ortiz-Boix, Carla
This article presents the results of an exploratory study which assesses the machine translation of audio descriptions as offering a possible solution to increase accessibility in multilingual environments. Accessibility is understood to encompass two different categories: sensorial accessibility (in this specific case, for the blind and visually impaired, who cannot access the visual content of audiovisual productions), and linguistic accessibility (for those who want to access this content in their own language). The article presents some thoughts on translation as a means of promoting multilingualism, on the feasibility of translating audio descriptions, and on machine translation as applied to this audiovisual translation mode, before summarising the findings of the present study and, most importantly, opening up new potential avenues for research., Este artículo presenta los resultados de un estudio exploratorio que evalúa la traducción automática de audiodescripciones como una posible solución para aumentar la accesibilidad en entornos multilingües. Se entiende que la accesibilidad abarca dos categorías diferentes: accesibilidad sensorial (en este caso específico, para los ciegos y discapacitados visuales, que no pueden acceder al contenido visual de las producciones audiovisuales) y accesibilidad lingüística (para aquellos que quieren acceder a este contenido en su propio idioma). El artículo presenta algunas reflexiones sobre la traducción como medio para promover el multilingüismo, sobre la viabilidad de traducir descripciones de audio y sobre la traducción automática tal y como se aplica a este tipo de traducción audiovisual, antes de sintetizar los hallazgos del presente estudio y, lo que es más importante, abrir la posibilidad de nuevas vías a la investigación.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Machine Translation and Audiovisual products, A case study

  • Martín Mor, Adrià|||0000-0003-0842-3190
  • Sánchez-Gijón, Pilar|||0000-0001-5919-4629
Much has been said and written about the effects that machine translation (MT) is having on all kinds of published products. This paper discusses the introduction of MT in the localisation of audiovisual products in general and particularly voiceover documentaries. Incorporating MT into the translation of voiceover documentaries would boost the dissemination of non-commercial or minority products, and could enhance the spread of culture. While it might at first seem that MT could be easily integrated into translation for documentaries, some particular aspects make it difficult to use MT to translate for dubbing or for voice-overs. We therefore designed an exploratory study using a corpus containing different texts of a film, in order to compare the results of different automatic measures. The preliminary results show that different results are obtained for different types of speech and that the application of automatic metrics produces similar results. In this article, we will present furthermore the methodological design, which might be considered useful for other studies of this kind
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Text-to-speech voice-over? A study on user preferences in the voicing of wildlife documentaries

  • Matamala, Anna|||0000-0002-1607-9011
  • Ortiz-Boix, Carla
In many countries the television broadcast of wildlife documentaries is nowadays translated from English and voiced by professional voice talents in the target language. This article discusses an alternative scenario in which text-to-speech would be used for the voicing of what is called "text-to-speech voice-over". It reports the results of an experiment in which a group of volunteers assessed excerpts voiced by synthetic voices as compared to excerpts voiced by human voices. Although human voices receive globally better assessments, results leave the door open to future research in the field
Dipòsit Digital de Documents de la UAB
Publication Capítulo o parte de un libro (BookPart)

Audio description from a Catalan perspective

Dipòsit Digital de Documents de la UAB
Publication Contribución de congreso (ConferenceOutput)

Researching audio description, User needs, technologies and new approaches

  • Matamala, Anna|||0000-0002-1607-9011
In this presentation I will offer an overview of audio description research carried out by TransMedia Catalonia at the Universitat Autònoma de Barcelona. Our research has explored not only descriptive aspects in audio description but has also delved into user reception and interaction. Technological developments, from analogue television to digital, immersive and blockchain, have guided our user-centric investigations, which have often focused on gathering user needs and testing different solutions. During my talk I will highlight the main results of our audio description research but will also briefly discuss our conceptualization of the user in accessibility and the relationship between technology and accessibility. I will also suggest innovative approaches to audio access services. In this regard, special emphasis will be put on a new concept of "easy audios" and how this concept can relate to existing audio descriptions.
Dipòsit Digital de Documents de la UAB
Publication Capítulo o parte de un libro (BookPart)

Audio Description and Accessibility Studies, A Work in Progress. New Approaches

  • Matamala, Anna|||0000-0002-1607-9011
  • Orero, Pilar|||0000-0003-0269-1936
This book is the second we have edited in English focusing on audio description (AD). Now the scope is diametrically different from the previous publication (Maszerowska, Matamala, & Orero, 2014), where one film was analysed from many perspectives. While the former could be considered to have followed a bottom-up approach, the present publication adopts a top-down approach. Audio Description: New Perspectives Illustrated looked at AD from the perspective of the many components in film language and narrative, its production and terminology. The result was an interesting in-depth analysis of 11 building blocks that need to be taken into consideration when embarking upon writing an AD script. The aim in the present book, in contrast, is to open the lens as widely as possible in order to take a panoramic picture of new approaches in current research in AD. The idea is also to set a long exposure time, hoping the photo will not be blurred. To understand fully the resulting image, though, there is a need to know what surrounds this image, in which field it was taken.