Busca

Road trippin' w ma 2 fav allies

Tag

Lavid

Accessibility as a Service: Augmenting Multimedia Content with Sign Language Video Tracks

Paper aceito em junho de 2012, finalmente publicado! 🙂

http://www.acs.org.au/information-resources/journal-library/jrpit/jrpit

http://www.acs.org.au/__data/assets/pdf_file/0020/51392/JRPIT45.2.79.pdf

Anúncios

Paper published – Information Sciences 2014

Paper resultante das pesquisas de Doutorado de Maritan, mestrado de Lacet e Danilo, e trabalho dos nossos projetos GT-AaaS (RNP) e outros.

 

Title – An Approach to Generate and Embed Sign Language Video Tracks into Multimedia Contents

Abstract. Deaf people have serious problems to access information due to their inherent diculties to deal with spoken and written languages. This work tries to address this problem by proposing a solution for automatic generation and insertion of sign language video tracks into captioned digital multimedia content. Our solution can process a subtitle stream and generate the sign language track in real-time. Furthermore, it has a set of mechanisms that exploit human computation to generate and maintain their linguistic
constructions. The solution was instantiated for the Digital TV, Web and Digital Cinema platforms and evaluated through a set of experiments with deaf users.
Keywords: Accessible multimedia contents, Brazilian Sign Language, machine translation, accessible technologies for the deaf, sign synthesis

 

Paper accepted – WCGA 2014 (SBRC)

XII Workshop de Computação em Clouds e Aplicações (WCGA 2014)
Florianópolis, 5 de Maio de 2014
Evento do Simpósio Brasileiro de Redes de Computadores (SBRC 2014)

Paper que descreve as estratégias para tolerância a falhas e provisionamento dinâmico de recursos para o VLIBRAS – DAaaS, resultado parcial do meu trabalho de mestrado. 

Título – Deaf Accessibility as a Service: uma Arquitetura Elástica e Tolerante a Falhas para o Sistema de Tradução VLIBRAS

Abstract. When designed, Information and Communication Technologies rarely take into account the barriers that deaf people face. Currently, there are tools for automatic translation from spoken languages to sign languages, but, unfortunately, they are not available to third parties. To reduce these problems, it would be interesting if any automatic translation service could be publicly available. This is the general goal of this work: use a preconceived machine translation from portuguese language to Brazilian Sign Language (LIBRAS), named VLIBRAS, and provide Deaf Accessibility as a Service publicly. The idea is to abstract inherent problems in the translation process between the portuguese language and LIBRAS by providing a service that performs the automatic translation of multimedia content to LIBRAS. VLIBRAS was primarily deployed as a centralized system, and this conventional architecture has some disadvantages when compared to distributed architectures. In this paper we propose a distributed architecture in order to provide an elastic service and achieve fault tolerance.

Anais do SBRC 2014: http://www.sbrc2014.ufsc.br/anais/files/anais_sbrc2014.pdf

PDCAT Presentation

http://prezi.com/dczanwh6v6dg/a-scalable-and-fault-tolerant-architecture-to-provide-deaf-a/#

Paper Accepted – PDCAT’13

PDCAT’13 – 14’th International Conference on Parallel and Distributed Computing, Applications and Technologies

Paper que descreve os objetivos e resultado parcial do meu trabalho de mestrado.

Título: A Scalable and Fault Tolerant Architecture to Provide Deaf Accessibility as a Service

Abstract—Deaf people face serious difficulties to access information. The fact is that they communicate naturally through sign languages, whereas, to most of them, the spoken languages are considered only a second language. When designed, Information and Communication Technologies (ICTs) rarely take into account the barriers that deaf people face. It is common that application developers do not hire sign languages interpreters to provide an accessible version of their app/site to deaf people. Currently, there are tools for automatic translation from sign languages to spoken languages, but, unfortunately, they are not available to third parties. To reduce these problems, it would be interesting if any automatic translation tool/service could be publicly available. This is the main goal of this work: use a preconceived machine translation from Portuguese Language to Brazilian Sign Language (LIBRAS) (named VLIBRAS) and provide Deaf Accessibility as a Service (DAaaS) publicly. The idea is to abstract inherent problems in the translation process between the Portuguese Language and LIBRAS by providing a service that performs the automatic translation of multimedia content to LIBRAS. VLIBRAS was primarily deployed as a centralized system, and this conventional architecture has some disadvantages when compared to distributed architectures. In this paper we propose two distributed architectures in order to provide a scalable service and achieve fault tolerance. For conception and availability of this service, it will be used the cloud computing paradigm to incorporate the following additional benefits: transparency, high availability, and efficient use of resources.

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6904279&tag=1

Paper Accepted – Journal of Research and Practice in Information Technology (2012)

Primeiro trabalho publicado que é realmente da área do meu mestrado. Depois vejo se posso postar o pdf aqui. =)

Title: Accessibility as a Service: Augmenting Multimedia Content with Sign Language Video Tracks

Abstract:
In this paper we explore the concept of “accessibility as a service” by proposing a cloud computing service to help deaf people to access digital contents. The proposed service automatically generates and embeds a sign language video track into multimedia contents. The service organizes the collaboration of sign language experts to dynamically adjust the system that runs on a cloud computing infrastructure. As a case study, we made an implementation of the service for providing support for the Brazilian Sign Language (LIBRAS) and some preliminary tests with Brazilian deaf users to evaluate the proposed solution.

Keywords: accessibility; sign language; machine translation; multimedia contents; cloud computing; sign animation.

 

Citação:

ARAÚJO, T. M. U., FERREIRA, F. L. S., SILVA, D.A.N.S., FALCÃO, E. L., DANTAS, L., DOMINGUES, L. A., LOPES, L. H. E., SATO, Y., LIMA, H. R., DUARTE, A. N., SOUZA FILHO, G. L.

Accessibility as a Service: Augmenting Multimedia Content with Sign Language Video Tracks. Journal of Research and Practice in Information Technology. , 2012.

Acessibilidade para Deficientes Auditivos

Um exemplo de vídeo final gerado pelo sistema do projeto GTAaaS. A partir de um vídeo e legenda (ou closed caption), o sistema faz a tradução automática da língua portuguesa para Libras, e acopla a janela ao vídeo original.

Processo de Tradução Automática da Língua Portuguesa para a LIBRAS

Seminário apresentado na disciplina de Teoria da Computação. Aborda de maneira resumida o processo de tradução da língua portuguesa para Libras, exemplificando as possíveis aplicações dos assuntos de Teoria da Computação no mesmo, como autômatos.

 

WRNP 2012

Ainda não tinha postado nada sobre a  viagem, então aqui vai um QuickPost só pra constar…

A cidade de Ouro Preto é bastante antiga, tendo sida tombada pelo patrimônio histórico. Sua beleza arquitetural é inegável, assim como suas ladeiras! Quem quiser passear “tem que ter pernas” e muito fôlego pra aguentar o tranco.. (kkkkkkkkkkk..)

Fora isso, e mais importante, a recepção dos nossos trabalhos foi ótima. Sentimos que todos se interessaram bastante, procuravam tirar dúvidas acerca de funcionamento, e dar palpites sobre como achavam poderíamos melhorar e incrementar o projeto. Enfim, foi uma experiência bem enriquecedora.

As fotos mais representativas da viagem estão na galeria abaixo, e o restante em http://www.flickr.com/photos/edufalcao/sets/72157629958581497/

That’s all folks!

Depois explico com mais detalhes a ideia do projeto e posto algum vídeo com a janela de tradução… =P

Blog no WordPress.com.

Acima ↑