Year: 2026
Type: conference-paper
Abstract: Consistency regularization (CR), which enforces agreement between model predictions on augmented views, has found recent benefits in automatic speech recognition [1]. In this paper, we propose the use of consistency regularization for audio event recognition, and demonstrate its effectiveness on AudioSet. With extensive ablation studies for both small (∼20k) and large (∼1.8M) supervised training sets, we show that CR brings consistent improvement over supervised baselines which already heavily utilize data augmentation, and CR using stronger augmentation and multiple augmentations leads to additional gain for the small training set. Furthermore, we extend the use of CR into the semi-supervised setup with 20K labeled samples and 1.8M unlabeled samples, and obtain performance improvement over our best model trained on the small set. Our code is available at https://github.com/shanmukasadhu/ModifiedAudioMAE
Authors: Shanmuka Sadhu, Weiran Wang
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: HORIZON EUROPE Health
OpenAlex ID: W4414597537
FWCI:
Cites:
Cited by:
Related to: