The SRI speaker recognition system for the 2008 NIST speaker recognition evaluation (SRE) incorporates a variety of models and features, both cepstral and stylistic. We highlight ...
Sachin S. Kajarekar, Nicolas Scheffer, Martin Grac...
We propose an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion. We motivate five simple cues designed to model specific patterns of motion and 3...
Gabriel J. Brostow, Jamie Shotton, Julien Fauqueur...
Structured models often achieve excellent performance but can be slow at test time. We investigate structure compilation, where we replace structure with features, which are often...
Word prediction performed by language models has an important role in many tasks as e.g. word sense disambiguation, speech recognition, hand-writing recognition, query spelling an...
We propose to improve speech recognition performance on speaker-independent, mixed language speech by asymmetric acoustic modeling. Mixed language is either inter-sentential code ...