We analyze subword-based language models (LMs) in large-vocabulary continuous speech recognition across four “morphologically rich” languages: Finnish, Estonian, Turkish, and ...
A conventional automatic speech recognizer does not perform well in the presence of multiple sound sources, while human listeners are able to segregate and recognize a signal of i...
Yang Shao, Soundararajan Srinivasan, Zhaozhang Jin...
This paper addresses the problem of markerless tracking of a human in full 3D with a high-dimensional (29D) body model. Most work in this area has been focused on achieving accura...
Patrick Peursum, Svetha Venkatesh, Geoff A. W. Wes...
The increasing use of distributed authentication architecture has made interoperability of systems an important issue. Interoperability of systems reflects the maturity of the tech...