Using N-Gram Analytics to Improve Automatic Fingerspelling Generation
نویسندگان
چکیده
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.
منابع مشابه
Improvement of generative adversarial networks for automatic text-to-image generation
This research is related to the use of deep learning tools and image processing technology in the automatic generation of images from text. Previous researches have used one sentence to produce images. In this research, a memory-based hierarchical model is presented that uses three different descriptions that are presented in the form of sentences to produce and improve the image. The proposed ...
متن کاملAutomatic feature generation and selection in predictive analytics solutions
In this thesis we proposed a feature generation and selection method called Feature Extraction and Selection for Predictive Analytics (FESPA). This method aims to improve the current Predictive Analytics solution of Quintiq, which had only options for manual feature selection and no options for feature generation. We have discovered that the proposed method does not decrease performance. In mos...
متن کاملEmpowering ELAN with N-gram Analytics for Corpora
American Sign Language, the preferred language of the Deaf community in the USA is its own language; complete with a rich collection of grammatical features. The DePaul University team has been working on an automatic English/ASL translator implemented as a 3D avatar in order to facilitate better communication between hearing and deaf people. Animations suffered from various timing inconsistenc...
متن کاملAn alternate approach towards meaningful lyric generation in Tamil
This paper presents our on-going work to improve the lyric generation component of the Automatic Lyric Generation system for the Tamil Language. An earlier version of the system used an n-gram based model to generate lyrics that match the given melody. This paper identifies some of the deficiencies in the melody analysis and text generation components of the earlier system and explains the new ...
متن کاملFostering Better Deaf/Hearing Communication through a Novel Mobile App for Fingerspelling
Fingerspelling is a critical communication of sign language used not only by deaf children but also by parents, teachers and interpreters who support them. The recognition of fingerspelling is particularly difficult for sign language learners and support software for practice is particularly limited due to the fluid and natural way that signers will spell with their hands. Any software tool tha...
متن کامل