ECHO: Environmental Sound Classification with Hierarchical Ontology-guided Semi-Supervised Learning

TL;DR

ECHO introduces a semi-supervised learning framework for environmental sound classification that leverages hierarchical label ontology and large language models to improve accuracy across multiple datasets.

Contribution

The paper presents a novel semi-supervised approach using ontology-guided pretext tasks and LLMs to enhance sound classification performance.

Findings

Achieves 1-8% accuracy improvement over baselines

Utilizes hierarchical label ontology for semantic learning

Effective across UrbanSound8K, ESC-10, and ESC-50 datasets

Abstract

Environment Sound Classification has been a well-studied research problem in the field of signal processing and up till now more focus has been laid on fully supervised approaches. Over the last few years, focus has moved towards semi-supervised methods which concentrate on the utilization of unlabeled data, and self-supervised methods which learn the intermediate representation through pretext task or contrastive learning. However, both approaches require a vast amount of unlabelled data to improve performance. In this work, we propose a novel framework called Environmental Sound Classification with Hierarchical Ontology-guided semi-supervised Learning (ECHO) that utilizes label ontology-based hierarchy to learn semantic representation by defining a novel pretext task. In the pretext task, the model tries to predict coarse labels defined by the Large Language Model (LLM) based on ground truth label ontology. The trained model is further fine-tuned in a supervised way to predict the actual task. Our proposed novel semi-supervised framework achieves an accuracy improvement in the range of 1\% to 8\% over baseline systems across three datasets namely UrbanSound8K, ESC-10, and ESC-50.