Selective Pseudo-labeling and Class-wise Discriminative Fusion for Sound Event Detection

TL;DR

This paper introduces a novel selective pseudo-labeling method and class-wise discriminative fusion to enhance sound event detection by effectively utilizing sound separation outputs, significantly improving performance on a standard dataset.

Contribution

The study proposes a new selective pseudo-labeling approach and a class-wise discriminative fusion method to improve sound event detection accuracy using sound separation outputs.

Findings

Significant improvements in F1, PSDS1, and PSDS2 scores on DCASE 2021 dataset.

Effective use of separated sound signals for better event detection.

Outperforms the official baseline in all evaluated metrics.

Abstract

In recent years, exploring effective sound separation (SSep) techniques to improve overlapping sound event detection (SED) attracts more and more attention. Creating accurate separation signals to avoid the catastrophic error accumulation during SED model training is very important and challenging. In this study, we first propose a novel selective pseudo-labeling approach, termed SPL, to produce high confidence separated target events from blind sound separation outputs. These target events are then used to fine-tune the original SED model that pre-trained on the sound mixtures in a multi-objective learning style. Then, to further leverage the SSep outputs, a class-wise discriminative fusion is proposed to improve the final SED performances, by combining multiple frame-level event predictions of both sound mixtures and their separated signals. All experiments are performed on the public DCASE 2021 Task 4 dataset, and results show that our approaches significantly outperforms the official baseline, the collar-based F 1, PSDS1 and PSDS2 performances are improved from 44.3%, 37.3% and 54.9% to 46.5%, 44.5% and 75.4%, respectively.