Página 1 dos resultados de 226 itens digitais encontrados em 0.005 segundos

Museum audio description

Martins, Cláudia Susana Nunes
Fonte: Transmedia Research Group Publicador: Transmedia Research Group
Tipo: Conferência ou Objeto de Conferência
ENG
Relevância na Pesquisa
66.44%
Audio description for the blind and visually impaired has been around since people have described what is seen. Throughout time, it has evolved and developed within different media, starting with reality and daily life, moving into the cinema and television, then across other performing arts, museums and art galleries, and public places. Thus, academics and entertainment providers have developed a growing interest for audio description, especially in what concerns the best methods and strategies to make words/texts give life to visual texts. The motto is to “make images verbal” or, within museum contexts, to make art (and not only) come alive for those who do not actually see. To them enjoyment might mean to see things through words. This presentation will focus on this particular form of intersemiotic translation.

Identificação automática de utilizadores com deficiência visual: a base para um serviço de áudio descrição personalizado; Automatic identification of visually impaired users: foundations for a costumized audio description service

Oliveira, Rita Alexandra Silva; Silva, Telmo Eduardo Miranda Castelão da; Abreu, Jorge Trinidad Ferraz de; Almeida, Ana Margarida Pisco
Fonte: Centro de Estudios en Comunicación, Información y Desarrollo (CIECID) y de la Unidad de Investigación en Marketing Aplicado de la Universidad de A Coruña Publicador: Centro de Estudios en Comunicación, Información y Desarrollo (CIECID) y de la Unidad de Investigación en Marketing Aplicado de la Universidad de A Coruña
Tipo: Artigo de Revista Científica
POR
Relevância na Pesquisa
66.62%
Os serviços de áudio descrição (AD) interativos, atualmente existentes, podem ser alvo de um conjunto de melhorias com vista a uma adequação mais eficiente ao contexto dos utilizadores com deficiência visual. Na realidade, as funcionalidades interativas inerentes a estes serviços, suportados por diferentes plataformas de televisão, centram-se, maioritariamente, na opção de ativação da áudio descrição e de alertas sonoros quando um programa com áudio descrição é iniciado. Contudo, as infraestruturas de distribuição de televisão atuais, desde que complementadas com um canal de retorno e Set-Top Boxes (STB) adequadas, abrem uma janela de oportunidade bastante interessante para a criação de um serviço interativo de áudio descrição que integre funcionalidades avançadas que possam ser, automaticamente, ajustadas às preferências dos utilizadores. É neste contexto que se propõe o desenvolvimento de um serviço interativo de áudio descrição complementado por um sistema de identificação automática do utilizador. Com esta complementaridade, o serviço pode ser dinamicamente ajustado às preferências do utilizador que, de facto, está a ver televisão, invocando, automaticamente, as opções previamente selecionadas nas respetivas configurações. Uma vez que existem diversas formas de implementar um sistema de identificação...

An iTV audio description service: suggesting requirements and features for visually impaired users

Oliveira, Rita Alexandra Silva; Abreu, Jorge Trinidad Ferraz de; Almeida, Ana Margarida Pisco
Fonte: Springer Berlin Heidelberg Publicador: Springer Berlin Heidelberg
Tipo: Parte de Livro
ENG
Relevância na Pesquisa
66.36%
The ongoing Digital Terrestrial Television (DTT) switchover leads to an interesting opportunity for the implementation of advanced television services. Actually, these services can even be interactive, since it is foreseen that the required Set-Top Boxes (STB) could be equipped with an Internet connection. However, among the future clients of DTT there are a large number of elderly and visually impaired people who can not entirely benefit of these services due to their physical limitations. Nevertheless, considering that Interactive Television (iTV) services can contribute to improve life quality of this type of users, it is essential to apply accessibility, usability and design-oriented guidelines for their development. In this context, this paper introduces a research related to universal design applied to iTV, being its aim to propose an advanced and accessible audio description service. In order to perceive the visually impaired users’ problems and needs, a group of individuals was asked to participate in an interview.

Audio Description and Automatic User Identification: a Promising Marriage in Digital Terrestrial Television (DTT)

Oliveira, Rita Alexandra Silva; Silva, Telmo Eduardo Miranda Castelão da; Abreu, Jorge Trinidad Ferraz de; Almeida, Ana MArgarida Pisco; Pacheco, Osvaldo Manuel da Rocha
Fonte: Universidad de Salamanca Publicador: Universidad de Salamanca
Tipo: Conferência ou Objeto de Conferência
ENG
Relevância na Pesquisa
66.39%
The DTT (Digital Terrestrial Television) switchover will enable the development of a television infrastructure with more resources and technological capabilities. In fact, DTT can encompass a variety of features and services where users can take on an interactive and participatory role. Nevertheless, the interactive services reveal interaction problems for visually impaired users (VIU). For this reason, it is important to apply accessibility, usability and design-oriented principles to the development of accessible interactive television systems. The present paper introduces a research project related to universal design issues on the Interactive Television scope, having as main objective the development of an audio description service offered by DTT that comprises an automatic identification system and an easy and simple interaction. Therefore, it will be prototyped an interactive and enhanced audio description system that includes new features and functionalities, is based on universal design principles and is supported by a users' identification system that is sustained through RFID tags and readers.

A tradução audiovisual: os desafios da áudio-descrição

Costa, Ana Margarete
Fonte: Instituto Politécnico do Porto. Instituto Superior de Contabilidade e Administração do Porto Publicador: Instituto Politécnico do Porto. Instituto Superior de Contabilidade e Administração do Porto
Tipo: Dissertação de Mestrado
Publicado em //2014 POR
Relevância na Pesquisa
56.63%
Dissertação de Mestrado apresentada ao Instituto Superior de Contabilidade e Administração do Porto para a obtenção do grau de Mestre em Tradução e Interpretação Especializadas, sob orientação de Doutora Sandra Ribeiro “Esta versão contém as críticas e sugestões dos elementos do júri.”; Nota: 18 valores; Sendo esta dissertação parte conclusiva do Mestrado em Tradução e Interpretação Especializadas, o objectivo da escolha deste tema pretende ser uma chamada de atenção para uma realidade: todas as pessoas têm o direito à comunicação e à informação de forma autónoma. A áudio-descrição é uma modalidade de tradução audiovisual ainda pouco conhecida e abordada em Portugal e fomenta a socialização entre os indivíduos, tornando-se relevante e útil para a sociedade. Este trabalho pretende abrir a discussão sobre as diferentes variantes de “olhar”, considerando a áudio-descrição como um recurso de acessibilidade que torna possível a compreensão das informações apreendidas visualmente. No âmbito de várias pesquisas que vêm sendo realizadas, com o fim de analisar aspectos importantes de recepção, de compreensão e de interpretação de resultados de produtos áudio-descritos por indivíduos com deficiência visual...

Ora, direis, ouvir imagens?: um olhar sobre o potencial informativo da áudio-descrição aplicada a obras de artes visuais bidimensionais como representação sonora da informação em arte para pessoas com deficiência visual

Mattoso, Verônica de Andrade
Fonte: Universidade Federal do Rio de Janeiro / Instituto Brasileiro de Informação em Ciência e Tecnologia; BR; Ciência da Informação; Programa de Pós-Graduação em Ciência da Informação; UFRJ/ECO - IBICT Publicador: Universidade Federal do Rio de Janeiro / Instituto Brasileiro de Informação em Ciência e Tecnologia; BR; Ciência da Informação; Programa de Pós-Graduação em Ciência da Informação; UFRJ/ECO - IBICT
Tipo: Dissertação Formato: application/pdf
POR
Relevância na Pesquisa
56.66%
Research about the informative potential of the audio description applied the two-dimensional works of visual arts as sonorous representation of the Information in Art for visually impaired people. Developed by means of a hybrid methodology composed by the approaches of the Evidential Paradigm, the Research-Action and on the basis of the Structural Model for Researches in Plastic Arts and in the Directives of the audio description for Samples and Museums it unfolded in methodological procedures in the which the researcher participated of diverse actions integrated to others agents. The inquiry sets out the extrinsic and inherent aspects of the audio description, considering the dimensions of accessibility physical, methodological, instrumental, communicative, programmatic and of attitudes by which means, the works of art, after being analyzed as sources of information and encoded in structure to assist, they become accessible and available to be accessed. A theoretical study about the stream informational audio description, carried out from the theoretical bases of the Information Science mainly of the Information in Art maintained the structure of the first exposition of two-dimensional works of visual arts with audio description that took place in the State of the Rio de Janeiro. The results of the research refute the distrust and the ignorance as to the informative potential that exists in the access of the visually impaired people to twodimensional standards and reveal contribution of the audio description for the Information Science. As byproduct of the research...

Audio description behaviour : universals, regularities and guidelines

Orero, Pilar
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: info:eu-repo/semantics/article; info:eu-repo/semantics/submittedVersion Formato: application/pdf
Publicado em //2012 ENG
Relevância na Pesquisa
66.62%
As the ad hoc narrative created for any media representation, dynamic or static, from a guided city tour of Barcelona to a Picasso painting, audio description is considered a form of semiotic translation; hence, some patterns and regularities should be observable both in its intermodal creation and its interlinguistic translation. While there is still only a small body of literature on audio description, audio-description guidelines seem to be one of the topics which have captured the interest of both academia and the professional world. There are now documents available for a number of countries which are concerned with the production and quality of audio-description scripts. Starting from the premise that audio description exhibits certain patterns or regularities, this article will look first at the concept of universals in Translation Studies, and how this concept can be extended to audio description. It then catalogues the many existing guidelines, which, if followed, should mark clear regularities in the audio description within a country – or language. After looking at some examples from existing norms and standards, we will explore some possible ways to define audio description universals for both theory and practical application...

The verbalizations of the effects of light and contrast in audio description

Maszerowska, Anna
Fonte: [Barcelona] : Universitat Autònoma de Barcelona, Publicador: [Barcelona] : Universitat Autònoma de Barcelona,
Tipo: Tesis i dissertacions electròniques; info:eu-repo/semantics/doctoralThesis; info:eu-repo/semantics/publishedVersion Formato: application/pdf
Publicado em //2014 ENG
Relevância na Pesquisa
66.59%
La interpretació del llenguatge cinematogràfic és de fa molt temps al centre de les investigacions centrades en l'audescripció. Mentre que molts investigadors han estudiat com els moviments de càmera, les tècniques d'edició i la composició del pla s'expressen als guions d'audiodescripció, la llum i el contrast, codis fonamentals del llenguatge fílmic, no han despertat fins ara massa interès acadèmic. Aquesta tesi té com a objectiu respondre a aquest buit parant esment a les estratègies emprades pels audiodescriptors quan s'enfronten amb configuracions d'il·luminació rellevants. A tal fi, al llarg del projecte de doctorat s'ha realitzat un estudi de cas múltiple de 13 pel·lícules amb audiodescripció. El corpus ha estat analitzat tenint en compte quatre categories generals de funcions de la il·luminació: puntuació argumental, percepció de l'escenari, percepció dels personatges i orientació de la mirada, totes elles prèviament identificades després d'un ampli escrutini de la literatura dels Estudis Fílmics. A la fase preliminar de la investigació, els fragments d'audescripció amb aspectes rellevants de configuració de la il·luminació pertanyen a un corpus de sis pel·lícules policíaques. En aquesta etapa de la recerca van sorgir dues macroestratègies per audiodescriure la llum: audiodescripció pròpiament descriptiva o audiodescripció centrada en l'efecte. A la segona fase...

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

Fernández i Torné, Anna; Matamala, Anna
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: Artigo de Revista Científica Formato: application/pdf
Publicado em //2015 ENG
Relevância na Pesquisa
56.49%
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.

Speaker diarization and speech recognition in the semi-automatization of audio description : an exploratory study on future possibilities?

Delgado Flores, Héctor; Matamala, Anna; Serrano, Javier
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: Artigo de Revista Científica Formato: application/pdf
Publicado em //2015 ENG
Relevância na Pesquisa
66.46%
This article presents an overview of the technological components used in the process of audio description, and suggests a new scenario in which speech recognition, machine translation, and text-to-speech, with the corresponding human revision, could be used to increase audio description provision. The article focuses on a process in which both speaker diarization and speech recognition are used in order to obtain a semi-automatic transcription of the audio description track. The technical process is presented and experimental results are summarized; Este artículo presenta una visión panorámica de los componentes tecnológicos usados en el proceso de audiodescripción y propone un nuevo escenario en el que se aplicarían el reconocimiento de habla, la traducción automática y la síntesis de habla, con su correspondiente revisión humana, para incrementar la cantidad de audiodescripciones disponibles. El artículo describe un proceso en el que la diarización y el reconocimiento de habla permiten obtener una transcripción semiautomática de la audiodescripción. El artículo presenta detalladamente el proceso técnico así como un resumen de los resultados experimentales.- In a second language

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

Matamala, Anna
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: Conferência ou Objeto de Conferência Formato: application/pdf
Publicado em //2015 ENG
Relevância na Pesquisa
66.4%
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...

Audio describing characters : what features do audiences remember?

Fresno Cañada, Nazaret; Castellà Mate, Judit; Matamala, Anna; Soler Vilageliu, Olga
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: Conferência ou Objeto de Conferência Formato: application/pdf
Publicado em //2015 ENG
Relevância na Pesquisa
56.57%
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...

Language without words : light and contrast in audio description

Maszerowska, Anna
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: Artigo de Revista Científica Formato: application/pdf
Publicado em //2013 ENG
Relevância na Pesquisa
66.49%
The importance of the inclusion of directorial vision and cinematographic language cues in film audio description scripts is a claim that has long been maintained in the literature related to media accessibility. This article aims to analyse the existing audio descriptions of light and contrast patterns. The first part presents an overview of the functions attributed to luminance in the field of Film Studies. The author then investigates the state of the art in the related literature on media accessibility and audio description. Guidelines and research papers are consulted in order to establish the stance on the issue from both a practical and scholarly point of view. The second part presents an analysis of a corpus of six professionally audio described films and discusses the strategies employed by the describers when confronted with certain lighting set-ups. Finally, the article concludes with a set of recommendations for future research in the area.

Less is more : effects of the amount of information and its presentation in the recall and reception of audio described characters

Fresno Cañada, Nazaret; Castellà Mate, Judit; Soler Vilageliu, Olga
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: Artigo de Revista Científica Formato: application/pdf
Publicado em //2014 ENG
Relevância na Pesquisa
56.53%
Audio description is a discipline within Translation Studies aimed at making audio visual products and events accessible to blind and visually impaired audiences. Works of art, TV programs, films and stage arts are audio described in order to guarantee that anyone, regardless of his/her visual capacity, can enjoy them. In the case of films, it consists of a verbal description of visual details such as settings and characters (what they look like, what they do and how they do it) provided to the audience in those parts of the movie where no relevant sounds or dialogues are heard. The nature of audio description, in which all the information is presented auditorily and at the fast pace usually imposed by films, might pose some challenges on users’ memory. This paper is an attempt to explore this issue empirically by focusing on audio described characters. It presents a reception study designed to explore how the amount of information included in the audio description of characters and its presentation have an effect on users’ recall. Results showed that limiting the information in the descriptions and dividing it into short units delivered at different stages of the AD favored users’ memory

Lyrics against images : music and audio description

Igareda Gonzalez, Paula
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: Artigo de Revista Científica Formato: application/pdf
Publicado em //2012 ENG
Relevância na Pesquisa
66.49%
Music has been an integral part of films from as far back as the silent movie era, where a piano accompaniment was used to build the narrative and an orchestra was used to drown out the sound of the projector. Music in films can encompass a wide array of elements, from a song to a whistle, and can play many roles, as has been commented upon by many researchers. Due to the relevance of music in film narrative, it is an element which merits attention when it comes to making a film accessible, be it through Audio description, Audio subtitling, Sign Language or Subtitling for the Deaf and Hard-of-Hearing. This article focuses on Audio description (AD) and how music is handled in audio described films. First of all, a brief review of existing AD guidelines will be presented in order to highlight the secondary role given to music insofar as these guidelines focus more on topics such as characters, locations, actions, credits, among others. This will be followed by an analysis of a corpus of audio described films, focusing on the treatment of songs with significant lyrics. Two different scenarios will be considered: on the one hand, films with song lyrics that can be understood by the audience because they share the same language and, on the other...

The present and future of audio description and subtitling for the deaf and hard of hearing in Spain

Utray Delgado, Francisco; Pereira Rodríguez, Ana M.; Orero, Pilar
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: Artigo de Revista Científica Formato: application/pdf
Publicado em //2009 ENG
Relevância na Pesquisa
66.29%
The aim of this article is to describe the state of the art in Spain of the two most popular media accessible modalities: audio description and subtitling for the deaf and hard of hearing. The article traces their origin and development up to the present time. It also examines standards and laws and analyses the economic and operative implications of media accessibility, which does not follow traditional economic parameters. The article aims to define the profile of future describers and subtitlers in Spain, who are currently being trained in the field of Audiovisual Translation. It concludes by proposing a wide variety of measures to be taken in order to reach full media accessibility and raise popular awareness of these services which are available now and will be increasingly so in the future with the change from analogous to digital broadcasting; Le présent article vise à faire le point sur les deux modes d’accessibilité aux médias les plus importants en Espagne : l’audiodescription et le sous-titrage pour sourds et malentendants. Il se reporte à l’origine de ces techniques, suit leur développement jusqu’à l’époque actuelle et examine les normes et les lois qui les régissent. Il propose une analyse des implications économiques et fonctionnelles de l’accessibilité aux médias...

The audio description of a Spanish phenomenon : Torrente 3

Orero, Pilar; Wharton, Steve
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: Artigo de Revista Científica Formato: application/pdf
Publicado em //2007 ENG
Relevância na Pesquisa
66.51%
While audio description as a technique has been round for centuries, its research in academia has just started. In some countries, such as Spain, norms and standards have been officially drafted before taking into consideration any scientific research results.This paper analyses some of the widely available audio description style sheets in Europe and the USA through a practical case: the creation of the audio description for the infamous Spanish film Torrente 3

Opera multimodal translation : audio describing Karel Szymanowski's Król Roger for the Liceu Theatre, Barcelona

Corral Fullà, Anna; Lladó, Ramón
Fonte: Universidade Autônoma de Barcelona Publicador: Universidade Autônoma de Barcelona
Tipo: Artigo de Revista Científica Formato: application/pdf
Publicado em //2011 ENG
Relevância na Pesquisa
56.36%
This paper discusses the use of audio description for opera working from a previously developed and tailored model that has been used in multimedia translation since 2005. It analyses the various integrated functions of this form of visual performance translation for the visually impaired, and explains the stages involved and what each stage entails. This is followed by a case study carried out at the Liceu Theatre in Barcelona involving the performance of Karol Szymanovski's Król Roger. The stage direction and set design of this opera are two key aspects of the production which are integral to an understanding of the plot and how it is conveyed through the language of music and words. This performance illustrates how one can make the best use of techniques designed for audio description—here, particular emphasis is given to the understanding, the conceptualising and the emotions expressed in the opera. It also underlines how the most important scenic information during the performance can be conveyed in such a way that it becomes accessible, functional, useful and easily perceptible to the listener who cannot see the stage directly. The audience is thus able to better appreciate and understand the performance as a whole

Audio description of films: experience, objectivity and cultural accessibility; Audiodescrição de filmes: experiência, objetividade e acessibilidade cultural

David, Jéssica; Instituto de Psicologia - Universidade Federal do Rio de Janeiro; Hautequestt, Felipe; Instituto de Psicologia - Universidade Federal do Rio de Janeiro; Kastrup, Virginia; Instituto de Psicologia - Universidade Federal do Rio de Janeiro
Fonte: Eduff Publicador: Eduff
Tipo: ; ; ; Avaliado por pares; Formato: application/pdf
Publicado em 30/04/2012 PT
Relevância na Pesquisa
66.46%
Nos últimos anos, tem-se observado uma preocupação crescente nos diversos setores da sociedade com a inclusão cultural dos deficientes visuais. São muitos os esforços voltados para o desenvolvimento de estratégias inclusivas que lhes permitam uma apropriação efetiva do espaço cultural. Entre tais iniciativas de acessibilidade, encontra-se a audiodescrição de filmes. O objetivo do artigo é propor algumas diretrizes para a audiodescrição, levando em conta peculiaridades cognitivas, bem como fatores sociais e políticos que cercam a vida de pessoas com deficiência visual. O artigo discute a experiência de assistir a um filme e analisa o problema da familiaridade com o cinema, com a narrativa de cada filme e com a própria técnica da audiodescrição. O desafio é criar condições favoráveis para a atualização de experiências cognitivas, afetivas e emocionais que o filme oferece. Visa ainda examinar o problema da objetividade e de outros parâmetros da audiodescrição, sugerindo algumas diretrizes para seu desenvolvimento no Brasil.; The aim of this paper is to propose guidelines for audio description, taking into account cognitive peculiarities, as well as social and political factors of people with visual impairment. The paper discusses the experience of watching a movie and analyses the problem of familiarity with the cinema...

Speaker diarization and speech recognition in the semi-automatization of audio description: An exploratory study on future possibilities?; Diarización y reconocimiento de habla en la semiautomatización de la audiodescripción: un estudio exploratorio sobre posibilidades futuras

Delgado, Héctor; Universitat Autònoma de Barcelona; Matamala, Anna; Universitat Autònoma de Barcelona; Serrano, Javier; Universitat Autònoma de Barcelona
Fonte: Universidade Federal de Santa Catarina Publicador: Universidade Federal de Santa Catarina
Tipo: info:eu-repo/semantics/article; info:eu-repo/semantics/publishedVersion; ; experimental and technological research; Formato: application/pdf
Publicado em 17/06/2015 ENG
Relevância na Pesquisa
66.53%
http://dx.doi.org/10.5007/2175-7968.2015v35n2p308This article presents an overview of the technological components used in the process of audio description, and suggests a new scenario in which speech recognition, machine translation, and text-to-speech, with the corresponding human revision, could be used to increase audio description provision. The article focuses on a process in which both speaker diarization and speech recognition are used in order to obtain a semi-automatic transcription of the audio description track. The technical process is presented and experimental results are summarized.; Este artículo presenta una visión panorámica de los componentes tecnológicos usados en el proceso de audiodescripción y propone un nuevo escenario en el que se aplicarían el reconocimiento de habla, la traducción automática y la síntesis de habla, con su correspondiente revisión humana, para incrementar la cantidad de audiodescripciones disponibles. El artículo describe un proceso en el que la diarización y el reconocimiento de habla permiten obtener una transcripción semiautomática de la audiodescripción. El artículo presenta detalladamente el proceso técnico así como un resumen de los resultados experimentales.