The nature of statistical learning theory
The nature of statistical learning theory
Shape quantization and recognition with randomized trees
Neural Computation
Machine Learning
Database-friendly random projections: Johnson-Lindenstrauss with binary coins
Journal of Computer and System Sciences - Special issu on PODS 2001
Information Theory, Inference & Learning Algorithms
Information Theory, Inference & Learning Algorithms
A toolbox for learning from relational data with propositional and multi-instance learners
AI'04 Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence
| Hi-index | 0.00 |
Speech recognition is among the harderst engineering problems,it has drawn the attention of various researchers over a wide range of fields. In our work we deviate from the mainstream methods by proposing a mixture of feature extraction and dimensionality reduction method based on Random Projections that is followed by widely used non-linear and probabilistic learning method,Random Forests that has been used successfully for high dimensional data in various applications of Machine Learning. The methodological strategy decouples the problem of speech recognition to 3 distinct components: a)feature extraction, b)dimensionality reduction,c)classification scheme,since tackles the problem via Statistical Learning Theory perspective enriched by the current advances of Signal Processing.