A Novel Approach for Effective Learning in Low Resourced Scenarios

Sri Harsha Dumpala; Rupayan Chakraborty; Sunil Kumar Kopparapu

A Novel Approach for Effective Learning in Low Resourced Scenarios

Computation and Language 2017-12-18 v1 Sound Audio and Speech Processing

Authors: Sri Harsha Dumpala , Rupayan Chakraborty , Sunil Kumar Kopparapu

Abstract

Deep learning based discriminative methods, being the state-of-the-art machine learning techniques, are ill-suited for learning from lower amounts of data. In this paper, we propose a novel framework, called simultaneous two sample learning (s2sL), to effectively learn the class discriminative characteristics, even from very low amount of data. In s2sL, more than one sample (here, two samples) are simultaneously considered to both, train and test the classifier. We demonstrate our approach for speech/music discrimination and emotion classification through experiments. Further, we also show the effectiveness of s2sL approach for classification in low-resource scenario, and for imbalanced data.

Keywords

low-resource learning deep learning simultaneous two sample learning class discriminative characteristics speech/music discrimination emotion classification imbalanced data

Cite

@article{arxiv.1712.05608,
  title  = {A Novel Approach for Effective Learning in Low Resourced Scenarios},
  author = {Sri Harsha Dumpala and Rupayan Chakraborty and Sunil Kumar Kopparapu},
  journal= {arXiv preprint arXiv:1712.05608},
  year   = {2017}
}

Comments

Presented at NIPS 2017 Machine Learning for Audio Signal Processing (ML4Audio) Workshop, Dec. 2017

A Novel Approach for Effective Learning in Low Resourced Scenarios

Abstract

Keywords

Cite

Comments

Related papers