DDSC: Dynamic Dual-Signal Curriculum for Data-Efficient Acoustic Scene Classification under Domain Shift

TL;DR

This paper introduces DDSC, an adaptive curriculum learning method for acoustic scene classification that dynamically adjusts training focus on domain-invariant and device-specific examples, improving cross-device accuracy.

Contribution

The paper proposes a novel online adaptive curriculum, DDSC, that combines domain-invariance and learning-progress signals to enhance data efficiency under domain shift in ASC.

Findings

DDSC improves cross-device performance across multiple baselines.

DDSC is lightweight and architecture-agnostic.

Largest gains observed on unseen-device splits.

Abstract

Acoustic scene classification (ASC) suffers from device-induced domain shift, especially when labels are limited. Prior work focuses on curriculum-based training schedules that structure data presentation by ordering or reweighting training examples from easy-to-hard to facilitate learning; however, existing curricula are static, fixing the ordering or the weights before training and ignoring that example difficulty and marginal utility evolve with the learned representation. To overcome this limitation, we propose the Dynamic Dual-Signal Curriculum (DDSC), a training schedule that adapts the curriculum online by combining two signals computed each epoch: a domain-invariance signal and a learning-progress signal. A time-varying scheduler fuses these signals into per-example weights that prioritize domain-invariant examples in early epochs and progressively emphasize device-specific cases. DDSC is lightweight, architecture-agnostic, and introduces no additional inference overhead. Under the official DCASE 2024 Task~1 protocol, DDSC consistently improves cross-device performance across diverse ASC baselines and label budgets, with the largest gains on unseen-device splits.