ECHO: Frequency-aware Hierarchical Encoding for Variable-length Signals

TL;DR

ECHO is a novel frequency-aware hierarchical encoding model for variable-length machine signals, achieving state-of-the-art results in anomaly detection and fault classification across diverse industrial datasets.

Contribution

The paper introduces ECHO, a foundation model with spectral localization and variable-length support, advancing machine signal modeling beyond existing approaches.

Findings

Achieves state-of-the-art anomaly detection performance

Supports arbitrary sampling rates and variable input lengths

Demonstrates strong generalization across multiple industrial datasets

Abstract

Pre-trained foundation models have demonstrated remarkable success in audio, vision and language, yet their potential for general machine signal modeling with arbitrary sampling rates-covering acoustic, vibration, and other industrial sensor data-remains under-explored. In this work, we propose a novel foundation model ECHO that integrates an advanced band-split architecture with frequency positional embeddings, enabling spectral localization across arbitrary sampling configurations. Moreover, the model incorporates sliding patches to support inputs of variable length without padding or cropping, producing a concise embedding that retains both temporal and spectral fidelity and naturally extends to streaming scenarios. We evaluate our method on various kinds of machine signal datasets, including previous DCASE task 2 challenges (2020-2025), and widely-used industrial signal corpora. Experimental results demonstrate consistent state-of-the-art performance in machine signal anomaly detection and fault classification, confirming the effectiveness and generalization capability of the proposed model. We open-sourced ECHO on https://github.com/yucongzh/ECHO.