Due to computational bounds, most SVM-based phonotactic language recognition systems consider only low-order n-grams (up to n = 3), thus limiting the potential performance of this...
This paper proposes a technique for improving tone correctness in Thai speech synthesis based on an average voice model trained with nonprofessional speech corpus. The proposed te...
—The advent of ubiquitous, mobile, personal devices creates an unprecedented opportunity to improve our understanding of human movement. In this work, we study human mobility in ...
When viewed from below, a user’s feet cast shadows onto the floor screen of an under-floor projection system, such as a sixsided CAVE. Tracking those shadows with a camera provi...
David J. Zielinski, Ryan P. McMahan, Rachel B. Bra...
Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid...
Carolina Parada, Mark Dredze, Abhinav Sethy, Ariya...