Improving Anomalous Sound Detection via Low-Rank Adaptation Fine-Tuning of Pre-Trained Audio Models

TL;DR

This paper enhances anomalous sound detection by fine-tuning pre-trained audio models with Low-Rank Adaptation, achieving state-of-the-art results and addressing data scarcity issues in industrial environments.

Contribution

It introduces the use of LoRA tuning for pre-trained audio models in ASD, significantly improving performance over previous methods.

Findings

Achieved 77.75% on DCASE2023 Task 2 dataset

Outperformed previous SOTA models by 6.48%

Validated effectiveness of LoRA tuning through ablation studies

Abstract

Anomalous Sound Detection (ASD) has gained significant interest through the application of various Artificial Intelligence (AI) technologies in industrial settings. Though possessing great potential, ASD systems can hardly be readily deployed in real production sites due to the generalization problem, which is primarily caused by the difficulty of data collection and the complexity of environmental factors. This paper introduces a robust ASD model that leverages audio pre-trained models. Specifically, we fine-tune these models using machine operation data, employing SpecAug as a data augmentation strategy. Additionally, we investigate the impact of utilizing Low-Rank Adaptation (LoRA) tuning instead of full fine-tuning to address the problem of limited data for fine-tuning. Our experiments on the DCASE2023 Task 2 dataset establish a new benchmark of 77.75% on the evaluation set, with a significant improvement of 6.48% compared with previous state-of-the-art (SOTA) models, including top-tier traditional convolutional networks and speech pre-trained models, which demonstrates the effectiveness of audio pre-trained models with LoRA tuning. Ablation studies are also conducted to showcase the efficacy of the proposed scheme.