SEED: Sound Event Early Detection via Evidential Uncertainty

TL;DR

This paper introduces PENet, a novel neural network that models evidential uncertainty for early sound event detection, improving reliability and accuracy in real-time acoustic environment recognition.

Contribution

The paper proposes a new evidential neural network with Beta distribution modeling and a backtrack inference method for enhanced early sound event detection.

Findings

Improved detection F1 score by 3.8% over state-of-the-art.

Reduced time delay by 13.0%.

Enhanced uncertainty modeling with evidential approach.

Abstract

Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes. However, most of the existing methods focus on the offline sound event detection, which suffers from the over-confidence issue of early-stage event detection and usually yield unreliable results. To solve the problem, we propose a novel Polyphonic Evidential Neural Network (PENet) to model the evidential uncertainty of the class probability with Beta distribution. Specifically, we use a Beta distribution to model the distribution of class probabilities, and the evidential uncertainty enriches uncertainty representation with evidence information, which plays a central role in reliable prediction. To further improve the event detection performance, we design the backtrack inference method that utilizes both the forward and backward audio features of an ongoing event. Experiments on the DESED database show that the proposed method can simultaneously improve 13.0\% and 3.8\% in time delay and detection F1 score compared to the state-of-the-art methods.