Audio Event and Scene Recognition: A Unified Approach using Strongly and Weakly Labeled Data

TL;DR

This paper introduces a unified learning framework that combines strongly and weakly labeled data for audio event and scene recognition, improving detection accuracy by leveraging limited fully labeled data alongside weak labels.

Contribution

The paper presents a novel SWSL framework and a graph-based manifold regularization method that effectively integrates weakly and strongly labeled data for audio analysis.

Findings

Improved accuracy in audio event detection using combined data labels.

Effective graph-based approach for semi-supervised learning.

Framework addresses challenges of weakly labeled audio data.

Abstract

In this paper we propose a novel learning framework called Supervised and Weakly Supervised Learning where the goal is to learn simultaneously from weakly and strongly labeled data. Strongly labeled data can be simply understood as fully supervised data where all labeled instances are available. In weakly supervised learning only data is weakly labeled which prevents one from directly applying supervised learning methods. Our proposed framework is motivated by the fact that a small amount of strongly labeled data can give considerable improvement over only weakly supervised learning. The primary problem domain focus of this paper is acoustic event and scene detection in audio recordings. We first propose a naive formulation for leveraging labeled data in both forms. We then propose a more general framework for Supervised and Weakly Supervised Learning (SWSL). Based on this general framework, we propose a graph based approach for SWSL. Our main method is based on manifold regularization on graphs in which we show that the unified learning can be formulated as a constraint optimization problem which can be solved by iterative concave-convex procedure (CCCP). Our experiments show that our proposed framework can address several concerns of audio content analysis using weakly labeled data.