Sciweavers

1585 search results - page 99 / 317
» Using a Non-prior Training Active Feature Model
Sort
View
EMNLP
2011
14 years 4 months ago
Universal Morphological Analysis using Structured Nearest Neighbor Prediction
In this paper, we consider the problem of unsupervised morphological analysis from a new angle. Past work has endeavored to design unsupervised learning methods which explicitly o...
Young-Bum Kim, João Graça, Benjamin ...
ISMIR
2003
Springer
133views Music» more  ISMIR 2003»
15 years 9 months ago
Chord segmentation and recognition using EM-trained hidden markov models
Automatic extraction of content description from commercial audio recordings has a number of important applications, from indexing and retrieval through to novel musicological ana...
Alexander Sheh, Daniel P. W. Ellis
NIPS
2004
15 years 5 months ago
Surface Reconstruction using Learned Shape Models
We consider the problem of geometrical surface reconstruction from one or several images using learned shape models. While humans can effortlessly retrieve 3D shape information, t...
Jan Erik Solem, Fredrik Kahl
IROS
2009
IEEE
201views Robotics» more  IROS 2009»
15 years 11 months ago
Modeling tool-body assimilation using second-order Recurrent Neural Network
— Tool-body assimilation is one of the intelligent human abilities. Through trial and experience, humans are capable of using tools as if they are part of their own bodies. This ...
Shun Nishide, Tatsuhiro Nakagawa, Tetsuya Ogata, J...
ICASSP
2011
IEEE
14 years 8 months ago
Use of VTL-wise models in feature-mapping framework to achieve performance of multiple-background models in speaker verification
Recently, Multiple Background Models (M-BMs) [1, 2] have been shown to be useful in speaker verification, where the M-BMs are formed based on different Vocal Tract Lengths (VTLs)...
Achintya Kumar Sarkar, Srinivasan Umesh