An Avatar-Based Weather Forecast Sign Language System for the Hearing-Impaired - Artificial Intelligence Applications and Innovations (AIAI 2014)
Conference Papers Year : 2014

An Avatar-Based Weather Forecast Sign Language System for the Hearing-Impaired

Juhyun Oh
  • Function : Author
  • PersonId : 992503
Seonggyu Jeon
  • Function : Author
  • PersonId : 992504
Minho Kim
  • Function : Author
  • PersonId : 992505
Hyukchul Kwon
  • Function : Author
  • PersonId : 992506
Iktae Kim
  • Function : Author
  • PersonId : 992507

Abstract

In this paper, we describe a text-to-animation framework for TV weather forecast sign language presentation. To this end, we analyzed the last three years’ weather forecast scripts to obtain the frequency of each word and determine the order of motion capture. About 500 sign language words were chosen and motion-captured for the weather forecast purpose, in addition to the existing 2,700 motions prebuilt for daily life. Words that are absent in the sign language dictionary are replaced with synonyms registered in KorLex, the Korean Wordnet, to improve the translation performance. The weather forecast with sign language is serviced via the Internet in an on-demand manner and can be viewed by PC or mobile devices.
Fichier principal
Vignette du fichier
978-3-662-44654-6_51_Chapter.pdf (1.08 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01391353 , version 1 (03-11-2016)

Licence

Identifiers

Cite

Juhyun Oh, Seonggyu Jeon, Minho Kim, Hyukchul Kwon, Iktae Kim. An Avatar-Based Weather Forecast Sign Language System for the Hearing-Impaired. 10th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2014, Rhodes, Greece. pp.519-527, ⟨10.1007/978-3-662-44654-6_51⟩. ⟨hal-01391353⟩
72 View
235 Download

Altmetric

Share

More