We build word models for American Sign Language (ASL) that transfer between different signers and different aspects. This is advantageous because one could use large amounts of la...
A computational model for learning languages in the limit from full positive data and a bounded number of queries to the teacher (oracle) is introduced and explored. Equivalence, ...
Modern computer games show potential not just for engaging and entertaining users, but also in promoting learning. Game designers employ a range of techniques to promote long-term ...
A framework is presented for discovering partial duplicates in large collections of scanned books with optical character recognition (OCR) errors. Each book in the collection is r...
We propose novel approaches for optimizing the detection performance in spoken language recognition. Two objective functions are designed to directly relate model parameters to tw...