Related projects

at Boston University

 

American Sign Language Linguistic Research Project

Investigation of the syntactic structure of ASL, with particular emphasis on the hierarchical representation of functional categories. Recent work has explored clausal structure: both the manual and non-manual expressions found with question phrases, tense, aspect, negation, and agreement.

Image and Video Computing Group

Research in the computer vision fields of person, head and skin tracking, and gesture recognition.

SignStream

SignStream™ is a database tool for analysis of linguistic data captured on video. SignStream provides a single computing environment for manipulating video and linking specific frame sequences to simultaneously occurring linguistic events encoded in a fine-grained, multi-level transcription. Designed for annotation and analysis of sign language and gesture, SignStream is distributed on a non-profit basis to educators, researchers, and students.

Essential Tools for Computational Research on Visual-Gestural Language Data (collaboration between C. Neidle and S. Sclaroff)

This project involves a Java reimplementation of SignStream to include tools for efficient data entry of fine-grained phonological information and integration of information provided by computer algorithms, among other new features. Machine vision-based algorithms for semi-automation of several aspects of the transcription process will also be developed.