Segment Relevance Estimation for Audio Analysis and Weakly-Labelled Classification

TL;DR

This paper introduces a relevance estimation method for audio segments in weakly-labelled classification, enabling adaptive, user-defined audio analysis without extra training, and proposes RELNET, a neural network leveraging this relevance for improved classification.

Contribution

The paper presents a novel relevance measure for audio segments that adapts to user-defined criteria without additional training, and introduces RELNET, a neural network architecture utilizing this measure for weakly-labelled audio classification.

Findings

RELNET achieved competitive results on DCASE2018 dataset.

The relevance measure effectively highlights important audio segments.

The method adapts to different user-defined viewpoints without retraining.

Abstract

We propose a method that quantifies the importance, namely relevance, of audio segments for classification in weakly-labelled problems. It works by drawing information from a set of class-wise one-vs-all classifiers. By selecting the classifiers used in each specific classification problem, the relevance measure adapts to different user-defined viewpoints without requiring additional neural network training. This characteristic allows the relevance measure to highlight audio segments that quickly adapt to user-defined criteria. Such functionality can be used for computer-assisted audio analysis. Also, we propose a neural network architecture, namely RELNET, that leverages the relevance measure for weakly-labelled audio classification problems. RELNET was evaluated in the DCASE2018 dataset and achieved competitive classification results when compared to previous attention-based proposals.