中文标题#
ECHO：面向频率的变长信号分层编码
英文标题#
ECHO: Frequency-aware Hierarchical Encoding for Variable-length Signal
中文摘要#
预训练基础模型在视觉和语言领域表现出色，但它们在通用机器信号建模方面的潜力 —— 涵盖声学、振动和其他工业传感器数据 —— 仍未得到充分探索。 现有的基于子带编码器的方法已取得有竞争力的结果，但受限于固定的输入长度，以及缺乏显式的频率位置编码。 在本工作中，我们提出了一种新颖的基础模型，该模型结合了先进的带分割架构与相对频率位置嵌入，能够在任意采样配置下实现精确的频谱定位。 该模型支持任意长度的输入，无需填充或分段，生成的嵌入表示保留了时间和频谱保真度。 我们在 SIREN（https://github.com/yucongzh/SIREN）上评估了我们的方法，这是一个新提出的用于机器信号编码的大规模基准，它统一了多个数据集，包括所有 DCASE 任务 2 挑战（2020-2025）和广泛使用的工业信号语料库。 实验结果表明，在异常检测和故障识别方面，我们的方法始终表现出最先进的性能，证实了所提出模型的有效性和泛化能力。 我们在 https://github.com/yucongzh/ECHO 上开源了 ECHO。
英文摘要#
Pre-trained foundation models have demonstrated remarkable success in vision and language, yet their potential for general machine signal modeling-covering acoustic, vibration, and other industrial sensor data-remains under-explored. Existing approach using sub-band-based encoders has achieved competitive results but are limited by fixed input lengths, and the absence of explicit frequency positional encoding. In this work, we propose a novel foundation model that integrates an advanced band-split architecture with relative frequency positional embeddings, enabling precise spectral localization across arbitrary sampling configurations. The model supports inputs of arbitrary length without padding or segmentation, producing a concise embedding that retains both temporal and spectral fidelity. We evaluate our method on SIREN (https://github.com/yucongzh/SIREN), a newly introduced large-scale benchmark for machine signal encoding that unifies multiple datasets, including all DCASE task 2 challenges (2020-2025) and widely-used industrial signal corpora. Experimental results demonstrate consistent state-of-the-art performance in anomaly detection and fault identification, confirming the effectiveness and generalization capability of the proposed model. We open-sourced ECHO on https://github.com/yucongzh/ECHO.
文章页面#
PDF 获取#
抖音扫码查看更多精彩内容