Sign language (SL) recognition modules in human-computer interaction systems need to be both fast and reliable. In cases where multiple sets of features are extracted from the SL d...
Sylvie C. W. Ong, David Hsu, Wee Sun Lee, Hanna Ku...
In the presence of environmental noise, speakers tend to adjust their speech production in an effort to preserve intelligible communication. The noise-induced speech adjustments, c...
Long-span language models that capture syntax and semantics are seldom used in the first pass of large vocabulary continuous speech recognition systems due to the prohibitive sea...
Anoop Deoras, Tomas Mikolov, Stefan Kombrink, Mart...
Cameras are ubiquitous everywhere and hold the promise of significantly changing the way we live and interact with our environment. Human activity recognition is central to under...
Octavia Camps, Mario Sznaier, Binlong Li, Teresa M...
We describe a novel semi-supervised method called WordCodebook Learning (WCL), and apply it to the task of bionamed entity recognition (bioNER). Typical bioNER systems can be seen...