DiffSED: Sound Event Detection with Denoising Diffusion
Preprint
Abstract
Sound Event Detection (SED) aims to predict the temporal boundaries of all the events of interest and their class labels, given an unconstrained audio sample. Taking either the splitand-classify (i.e., frame-level) strategy or the more principled event-level modeling approach, all existing methods consider the SED problem from the discriminative learning perspective. In this work, we reformulate the SED problem by taking a generative learning perspective. Specifically, we aim to generate sound temporal boundaries from noisy proposals in a denoising diffusion process, conditioned on a target audio sample. During training, our model learns to reverse the noising process by converting noisy latent queries to the groundtruth versions in the elegant Transformer decoder framework. Doing so enables the model generate accurate event boundaries from even noisy queries during inference. Extensive experiments on the Urban-SED and EPIC-Sounds datasets demonstrate that our model significantly outperforms existing alternatives, with 40+% faster convergence in training.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- DiffusionDet: Diffusion Model for Object Detection2023
- A Novel Metric For Evaluating Audio Caption Similarity2023
- Analysing Diffusion-based Generative Approaches Versus Discriminative Approaches for Speech Restoration2023
- ReAct: Temporal Action Detection with Relational Queries2022
- CNN-Transformer with Self-Attention Network for Sound Event Detection2022
- Slow-Fast Auditory Streams for Audio Recognition2021
- Text-to-Audio Grounding: Building Correspondence Between Captions and Sound Events2021
- Sound Event Detection by Consistency Training and Pseudo-Labeling With Feature-Pyramid Convolutional Recurrent Neural Networks2021
- SOLO: Segmenting Objects by Locations2020
- Knowledge Transfer from Weakly Labeled Audio Using Convolutional Neural Network for Sound Events and Scenes2018