Sciweavers

3641 search results - page 297 / 729
» On Computability of Pattern Recognition Problems
Sort
View
ECCV
1998
Springer
16 years 9 months ago
A Probabilistic Approach to Object Recognition Using Local Photometry and Global Geometry
Many object classes, including human faces, can be modeled as a set of characteristic parts arranged in a variable spatial con guration. We introduce a simpli ed model of a deforma...
Michael C. Burl, Markus Weber, Pietro Perona
ICPR
2006
IEEE
16 years 8 months ago
Switching Auxiliary Chains for Speech Recognition based on Dynamic Bayesian Networks
This paper investigates the problem of incorporating auxiliary information (e.g. pitch) for speech recognition using dynamic Bayesian networks (DBNs). Previous works usually model...
Hui Lin 0001, Zhijian Ou
ICPR
2006
IEEE
16 years 8 months ago
Multilinear Principal Component Analysis of Tensor Objects for Recognition
In this paper, a multilinear formulation of the popular Principal Component Analysis (PCA) is proposed, named as multilinear PCA (MPCA), where the input can be not only vectors, b...
Anastasios N. Venetsanopoulos, Haiping Lu, Konstan...
ICPR
2000
IEEE
16 years 8 months ago
A Markov Random Field Model for Automatic Speech Recognition
Speech can be represented as a time/frequency distribution of energy using a multi-band filter bank. A Markov random field model, which takes into account the possible time asynch...
Gérard Chollet, Guillaume Gravier, Marc Sig...
ICPR
2008
IEEE
16 years 1 months ago
Learning polynomial function based neutral-emotion GMM transformation for emotional speaker recognition
One of the biggest challenges in speaker recognition is dealing with speaker-emotion variability. The basic problem is how to train the emotion GMMs of the speakers from their neu...
Zhenyu Shan, Yingchun Yang