AudioCIL: A Python Toolbox for Audio Class-Incremental Learning with Multiple Scenes

TL;DR

AudioCIL is a Python toolbox designed to facilitate audio class-incremental learning, enabling models to adapt to new audio classes over time without forgetting previous knowledge, thus better reflecting real-world audio environment dynamics.

Contribution

The paper introduces AudioCIL, a new Python toolbox that supports audio class-incremental learning, bridging the gap between static datasets and real-world streaming audio scenarios.

Findings

Provides a flexible framework for incremental learning in audio tasks

Enables models to learn new classes without forgetting old ones

Supports research in real-world audio environment adaptation

Abstract

Deep learning, with its robust aotomatic feature extraction capabilities, has demonstrated significant success in audio signal processing. Typically, these methods rely on static, pre-collected large-scale datasets for training, performing well on a fixed number of classes. However, the real world is characterized by constant change, with new audio classes emerging from streaming or temporary availability due to privacy. This dynamic nature of audio environments necessitates models that can incrementally learn new knowledge for new classes without discarding existing information. Introducing incremental learning to the field of audio signal processing, i.e., Audio Class-Incremental Learning (AuCIL), is a meaningful endeavor. We propose such a toolbox named AudioCIL to align audio signal processing algorithms with real-world scenarios and strengthen research in audio class-incremental learning. Code is available at https://github.com/colaudiolab/AudioCIL.