Linguistics and Literature Studies Vol. 5(3), pp. 187 - 197
DOI: 10.13189/lls.2017.050306
Reprint (PDF) (585Kb)

Using N-Gram Analytics to Improve Automatic Fingerspelling Generation

John McDonald ^*, Rosalee Wolfe , Souad Baowidan , Ningshan Guo , Sarah Johnson , Robyn Moncrief
School of Computing, DePaul University, United States

ABSTRACT

Fingerspelling recognition is one of the last skills acquired, due to the complex nature of fingerspelling and a lack of display technology that is sufficiently natural for recognition practice. This paper describes a corpus-based study utilizing an n-gram extension to ELAN to gain a deeper understanding of deletion and coarticulation in fingerspelling. The analysis shows that coarticulation and deletion increase with fingerspelling speed and that deletions form an increasing percentage of the modifications at shorter durations. Insights from the study informed strategies to improve current avatar-based fingerspelling generation.

KEYWORDS
Fingerspelling, Corpus Analysis, Sign Language animation, Interpreter Training

Cite This Paper in IEEE or APA Citation Styles
(a). IEEE Format:
[1] John McDonald , Rosalee Wolfe , Souad Baowidan , Ningshan Guo , Sarah Johnson , Robyn Moncrief , "Using N-Gram Analytics to Improve Automatic Fingerspelling Generation," Linguistics and Literature Studies, Vol. 5, No. 3, pp. 187 - 197, 2017. DOI: 10.13189/lls.2017.050306.

(b). APA Format:
John McDonald , Rosalee Wolfe , Souad Baowidan , Ningshan Guo , Sarah Johnson , Robyn Moncrief (2017). Using N-Gram Analytics to Improve Automatic Fingerspelling Generation. Linguistics and Literature Studies, 5(3), 187 - 197. DOI: 10.13189/lls.2017.050306.