Active learning strategies can be useful when manual labeling
effort is scarce, as they select the most informative
examples to be annotated first. However, for visual category
...
Sudheendra Vijayanarasimhan (University of Texas a...
The best performing systems in the area of automatic speaker recognition have focused on using short-term, low-level acoustic information, such as sepstral features. Recently, vari...
This paper presents a new deterministic approximation technique in Bayesian networks. This method, "Expectation Propagation," unifies two previous techniques: assumed-de...
Code synthesis is routinely used in industry to generate GUIs, form lling applications, and database support code and is even used with COBOL. In this paper we consider the questi...
Wray L. Buntine, Bernd Fischer 0002, Thomas Pressb...
This paper presents a bottom-up approach that combines audio and video to simultaneously locate individual speakers in the video (2-D source localization) and segment their speech ...