Sciweavers

1014 search results - page 121 / 203
» A Spectral Algorithm for Learning Hidden Markov Models
Sort
View
JMLR
2008
188views more  JMLR 2008»
13 years 7 months ago
Maximal Causes for Non-linear Component Extraction
We study a generative model in which hidden causes combine competitively to produce observations. Multiple active causes combine to determine the value of an observed variable thr...
Jörg Lücke, Maneesh Sahani
ICDAR
2003
IEEE
14 years 1 months ago
Optimizing the Number of States, Training Iterations and Gaussians in an HMM-based Handwritten Word Recognizer
In off-line handwriting recognition, classifiers based on hidden Markov models (HMMs) have become very popular. However, while there exist well-established training algorithms, s...
Simon Günter, Horst Bunke
ICDAR
2007
IEEE
14 years 2 months ago
Handwritten Word Recognition Using Conditional Random Fields
The paper describes a lexicon driven approach for word recognition on handwritten documents using Conditional Random Fields(CRFs). CRFs are discriminative models and do not make a...
Shravya Shetty, Harish Srinivasan, Sargur N. Sriha...
AIHC
2007
Springer
14 years 1 months ago
Audio-Visual Spontaneous Emotion Recognition
Automatic multimodal recognition of spontaneous emotional expressions is a largely unexplored and challenging problem. In this paper, we explore audio-visual emotion recognition in...
Zhihong Zeng, Yuxiao Hu, Glenn I. Roisman, Zhen We...
IJCNN
2006
IEEE
14 years 1 months ago
Reservoir-based techniques for speech recognition
— A solution for the slow convergence of most learning rules for Recurrent Neural Networks (RNN) has been proposed under the terms Liquid State Machines (LSM) and Echo State Netw...
David Verstraeten, Benjamin Schrauwen, Dirk Stroob...