Style transfer combines the content of one signal with the style of another. It supports applications such as data augmentation and scenario simulation, helping machine learning models generalize in data-scarce domains. While well developed in vision and language, style transfer methods for time series data remain limited. We introduce DiffTSST, a diffusion-based framework that disentangles a time series into content and style representations via convolutional encoders and recombines them through a self-supervised attention-based diffusion process. At inference, encoders extract content and style from two distinct series, enabling conditional generation of novel samples to achieve style transfer. We demonstrate both qualitatively and quantitatively that DiffTSST achieves effective style transfer. We further validate its real-world utility by showing that data augmentation with DiffTSST improves anomaly detection in data-scarce regimes.
@article{arxiv.2510.11335,
title = {DiffStyleTS: Diffusion Model for Style Transfer in Time Series},
author = {Mayank Nagda and Phil Ostheimer and Justus Arweiler and Indra Jungjohann and Jennifer Werner and Dennis Wagner and Aparna Muraleedharan and Pouya Jafari and Jochen Schmid and Fabian Jirasek and Jakob Burger and Michael Bortz and Hans Hasse and Stephan Mandt and Marius Kloft and Sophie Fellenz},
journal= {arXiv preprint arXiv:2510.11335},
year = {2025}
}