The Mechanics of Fingerspelling: Analyzing Ethiopian Sign Language
A discussion of the Ethiopian Sign Language (ETH) fingerspelling system. Folowing the CV (consonant-vowel) structure of Amharic (the majority spoken language of Ethiopia), ETH creates whole signs that represent a syllabic orthography. Hand Configurations correspond to consonants and Timing, Placement, and Orientation clusters correspond to vowels.
A Combined Semantic and Motion Capture Database for Real-Time Sign Language Synthesis Accepted as a short paper for IVA ‘09
An analysis of database structure and query approaches for the real-time synthesis of French Sign Language (LSF) streams from previously-recorded motion capture data. A database is constructed from raw motion files and their corresponding annotation files, giving access to both form and meaning. Novel sign sequences can be constructed from queries of stored signs, though transitions must be created on-line.
Gérard: Interacting with Users of French Sign Language Accepted for GALA ‘09
Our aim is to implement a motion capture database for the synthesis of virtual agents signing in French Sign Language (LSF), taking into account the semantic information implicitly contained in language data. The Gérard system is a first iteration along the path toward efficient and convincing animations of an LSF signer.
Publications
In Progress
Forthcoming
The Mechanics of Fingerspelling: Analyzing Ethiopian Sign Language
A discussion of the Ethiopian Sign Language (ETH) fingerspelling system. Folowing the CV (consonant-vowel) structure of Amharic (the majority spoken language of Ethiopia), ETH creates whole signs that represent a syllabic orthography. Hand Configurations correspond to consonants and Timing, Placement, and Orientation clusters correspond to vowels.
A Combined Semantic and Motion Capture Database for Real-Time Sign Language Synthesis
Accepted as a short paper for IVA ‘09
An analysis of database structure and query approaches for the real-time synthesis of French Sign Language (LSF) streams from previously-recorded motion capture data. A database is constructed from raw motion files and their corresponding annotation files, giving access to both form and meaning. Novel sign sequences can be constructed from queries of stored signs, though transitions must be created on-line.
Gérard: Interacting with Users of French Sign Language
Accepted for GALA ‘09
Our aim is to implement a motion capture database for the synthesis of virtual agents signing in French Sign Language (LSF), taking into account the semantic information implicitly contained in language data. The Gérard system is a first iteration along the path toward efficient and convincing animations of an LSF signer.