Sound event detection based on auxiliary decoder and maximum probability aggregation for DCASE Challenge 2024 Task 4

TL;DR

This paper introduces three innovative methods for sound event detection in the DCASE 2024 Challenge, including an auxiliary decoder, maximum probability aggregation, and multi-channel features, to improve robustness and dataset adaptability.

Contribution

The paper presents novel auxiliary decoder, MPA technique, and multi-channel features to enhance SED model performance and dataset compatibility.

Findings

Improved SED performance across datasets.

Enhanced feature extraction with auxiliary decoder.

Effective alignment of soft labels using MPA.

Abstract

In this report, we propose three novel methods for developing a sound event detection (SED) model for the DCASE 2024 Challenge Task 4. First, we propose an auxiliary decoder attached to the final convolutional block to improve feature extraction capabilities while reducing dependency on embeddings from pre-trained large models. The proposed auxiliary decoder operates independently from the main decoder, enhancing performance of the convolutional block during the initial training stages by assigning a different weight strategy between main and auxiliary decoder losses. Next, to address the time interval issue between the DESED and MAESTRO datasets, we propose maximum probability aggregation (MPA) during the training step. The proposed MPA method enables the model's output to be aligned with soft labels of 1 s in the MAESTRO dataset. Finally, we propose a multi-channel input feature that employs various versions of logmel and MFCC features to generate time-frequency pattern. The experimental results demonstrate the efficacy of these proposed methods in a view of improving SED performance by achieving a balanced enhancement across different datasets and label types. Ultimately, this approach presents a significant step forward in developing more robust and flexible SED models