发表机构
MERL（三菱电机研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出NA-SSL模型，用于NA-ASD任务，在DCASE 2026挑战赛任务2数据集上，NA-BEATs系统以70.24%的官方得分大幅领先，验证了所提方法的有效性。
AI 中文摘要
本文提出噪声感知自监督学习（NA-SSL）模型，用于噪声感知异常声音检测（NA-ASD）。NA-ASD是一项采用双通道音频录制的异常声音检测（ASD）任务，其中一个麦克风靠近目标机器，另一个则放置在较远位置以采集噪声。针对该任务，我们利用多样化音频数据集模拟双通道录制数据，并训练NA-SSL模型，将受背景噪声主导的远麦克风录制信号作为辅助信息，提取近麦克风信号的纯净自监督学习（SSL）表示。随后，NA-SSL模型被用作标准ASD框架的前端。我们在DCASE 2026挑战赛任务2开发数据集上开展实验评估，结果表明，NA-SSL框架在三种基础SSL模型（BEATs、EAT和Dasheng）上均表现有效，无论是否经过判别式微调。此外，挑战赛结果也验证了该方法的有效性：NA-BEATs系统以大幅优势赢得挑战赛，官方得分达70.24%，而第二名系统得分仅为65.46%。
英文摘要
In this paper, we introduce noise-aware self-supervised learning (NA-SSL) models for noise-aware anomalous sound detection (NA-ASD). NA-ASD is an ASD task with two-channel audio recordings, where one microphone is located close to the target machine and the other is located farther away to capture noise. For this task, we simulate two-channel recordings using diverse audio datasets and train NA-SSL models to extract clean SSL representations of the close-microphone signal by using the far-microphone recording dominated by background noise as auxiliary information. The NA-SSL models are then used as frontends in the standard ASD framework. Our experimental evaluation on the DCASE 2026 Challenge Task 2 development dataset demonstrates the effectiveness of the NA-SSL framework across three base SSL models (BEATs, EAT, and Dasheng), both with and without discriminative fine-tuning. Furthermore, the challenge results proved the effectiveness of the proposed approach, where the NA-BEATs system won the challenge by a large margin, achieving an official score of 70.24%, while the second-place system achieved 65.46%.
CommentsAccepted to DCASE Workshop 2026
