In this paper a complete OCR methodology for recognizing historical documents, either printed or handwritten without any knowledge of the font, is presented. This methodology cons...
We present a discriminative part-based approach for the recognition of object classes from unsegmented cluttered scenes. Objects are modeled as flexible constellations of parts co...
A recent area of significant progress in speaker recognition is the use of high level features—idiolect, phonetic relations, prosody, discourse structure, etc. A speaker not on...
William M. Campbell, Joseph P. Campbell, Douglas A...
Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approa...
Lukas Burget, Petr Schwarz, Mohit Agarwal, Pinar A...
Motivation Protein remote homology prediction and fold recognition are central problems in computational biology. Supervised learning algorithms based on support vector machines a...