The Sound of Noise: Leveraging the Inductive Bias of Pre-trained Audio Transformers for Glitch Identification in LIGO

2026-01-27

AI Summary

This work addresses the challenge of transient noise (glitches) in gravitational-wave detection, which can mimic or obscure true astrophysical signals and are typically identified using methods reliant on extensive manual labeling with limited generalization. For the first time, we adapt the large-scale pre-trained Audio Spectrogram Transformer (AST)—originally developed for audio classification—to gravitational-wave data analysis by treating strain time series as audio signals. Leveraging AST’s inductive bias from natural sound representations, we combine time–frequency spectrogram inputs with unsupervised t-SNE clustering. Evaluation on LIGO O3/O4 data demonstrates that AST-derived embeddings effectively separate glitches from genuine signals, with clustering outcomes highly consistent with Gravity Spy labels. This approach significantly enhances the identification of novel glitch morphologies and rare signals while improving data efficiency.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Natural Language Processing: Speech
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Transient noise artifacts, or glitches, fundamentally limit the sensitivity of gravitational-wave (GW) interferometers and can mimic true astrophysical signals, particularly the short-duration intermediate-mass black hole (IMBH) mergers. Current glitch classification methods, such as Gravity Spy, rely on supervised models trained from scratch using labeled datasets. These approaches suffer from a significant ``label bottleneck,"requiring massive, expertly annotated datasets to achieve high accuracy and often struggling to generalize to new glitch morphologies or exotic GW signals encountered in observing runs. In this work, we present a novel cross-domain framework that treats GW strain data through the lens of audio processing. We utilize the Audio Spectrogram Transformer (AST), a model pre-trained on large-scale audio datasets, and adapt it to the GW domain. Instead of learning time-frequency features from scratch, our method exploits the strong inductive bias inherent in pre-trained audio models, transferring learned representations of natural sound to the characterization of detector noise and GW signals, including IMBHs. We validate this approach by analyzing strain data from the third (O3) and fourth (O4) observing runs of the LIGO detectors. We used t-Distributed Stochastic Neighbor Embedding (t-SNE), an unsupervised clustering technique, to visualize the AST-derived embeddings of signals and glitches, revealing well-separated groups that align closely with independently validated Gravity Spy glitch classes. Our results indicate that the inductive bias from audio pre-training allows superior feature extraction compared to traditional supervised techniques, offering a robust, data-efficient pathway for discovering new, anomalous transients, and classifying complex noise artifacts in the era of next-generation detectors.

Problem

• glitch identification
• gravitational-wave detectors
• label bottleneck
• transient noise
• signal classification

Innovation

• Audio Spectrogram Transformer
• inductive bias
• glitch classification
• cross-domain transfer
• gravitational-wave data