We describe a system for separating multiple sources from a two-channel recording based on interaural cues and prior knowledge of the statistics of the underlying source signals. ...
Ron J. Weiss, Michael I. Mandel, Daniel P. W. Elli...
We describe the underlying probabilistic generative signal model of non-negative matrix factorisation (NMF) and propose a realistic conjugate priors on the matrices to be estimate...
Tuomas Virtanen, Ali Taylan Cemgil, Simon J. Godsi...
Current object recognition systems can only recognize a limited number of object categories; scaling up to many categories is the next challenge. We seek to build a system to reco...
Bryan C. Russell, Antonio Torralba, Ce Liu, Robert...
We have developed a method for answering single answer questions automatically using a collection of documents or the Internet as a source of data for the production of the answer...
James R. Cowie, Yevgeny Ludovik, Hugo Molina-Salga...
Spoken language is one of the most intuitive forms of interaction between humans and agents. Unfortunately, agents that interact with people using natural language often experienc...