A Novel Approach for Effective Learning in Low Resourced Scenarios

TL;DR

This paper introduces s2sL, a novel framework that improves learning from limited data by considering multiple samples simultaneously, demonstrating effectiveness in speech/music discrimination, emotion classification, and imbalanced data scenarios.

Contribution

The paper presents a new simultaneous two sample learning (s2sL) framework that enhances class discrimination in low-resource and imbalanced data settings.

Findings

s2sL outperforms traditional methods in low-resource scenarios

Effective for speech/music discrimination and emotion classification

Improves classification accuracy with limited and imbalanced data

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.