Recently, Deep Belief Networks (DBNs) have been proposed for phone recognition and were found to achieve highly competitive performance. In the original DBNs, only framelevel info...
Probabilistic grammars offer great flexibility in modeling discrete sequential data like natural language text. Their symbolic component is amenable to inspection by humans, while...
We present an approach to music identification based on weighted finite-state transducers and Gaussian mixture models, inspired by techniques used in large-vocabulary speech recogn...
—Patterns of human encounters, which are difficult to observe directly, are fundamental to the propagation of mobile malware aimed at infecting devices in spatial proximity. We ...
James Mitchell, Eamonn O'Neill, Gjergji Zyba, Geof...
We set out to examine whether current, DRM-based online offerings of music and movies accord with consumers’ current expectations regarding the personal use of copyrighted works...