A serious problem in learning probabilistic models is the presence of hidden variables. These variables are not observed, yet interact with several of the observed variables. As s...
Gal Elidan, Noam Lotner, Nir Friedman, Daphne Koll...
This paper presents work done at Cambridge University, on the TREC7 Spoken Document Retrieval (SDR) Track. The broadcast news audio was transcribed using a 2-pass gender-dependent...
Sue E. Johnson, P. Jourlin, G. L. Moore, Karen Spa...
Abstract In this paper, we propose a microprocessor architecture which eciently utilizes nextgeneration semiconductor technology. While the technology makes it possible to integrat...
A principal problem of auditory scene analysis is stream segregation: decomposing an input acoustic signal into signals of individual sound sources included in the input. While ex...
Because observing the same actions can warrant different conclusions depending on who executed the actions, a goal recognizer that works well on one person might not work well on ...