Time-warping estimation via stationarity-based learning of the de-warped signal
Abstract
Time-warping estimation is a fundamental problem in signal processing with applications in bioacoustics, radar, and biomedical analysis. This paper introduces a Time-Warping Estimation Trainable (TWET) model for estimating timewarping functions from a single observation. The proposed approach formulates time-warping estimation as a stationarization problem in the wavelet domain and leverages a hierarchical dilated convolutional architecture to estimate the time-warping functions. A differentiable stationarity criterion is introduced for end-to-end optimization. TWET is compared with existing approaches. Experimental results show improved deformation reconstruction accuracy together with significantly reduced computation time, making the framework compatible with low-latency applications.
Related
- Learning on-the-fly quasi-stationarity diagnostics from low-dimensional surrogates
- Near-Optimal Learning of Quantum Many-Body Systems from Gibbs and Thermal Metastable States via the Stationarity Test
- On Unbiased Parameter Estimation and Signal Reconstruction
- A Sharp Signal-to-Noise Threshold for Quasi-Maximum Likelihood Breakpoint Estimation
- Particle-Number-Preserving Quantum Signal Processing for Thermal Properties: Canonical-Ensemble Estimation and Grand-Canonical Reconstruction
BibTeX
@misc{presvots2026timewarping,
title = {{Time-warping estimation via stationarity-based learning of the de-warped signal}},
author = {Corentin Presvôts and Adrien Meynard},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.16796},
eprint = {2609.16796},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.16796},
}
RIS
TY - UNPB
TI - Time-warping estimation via stationarity-based learning of the de-warped signal
AU - Corentin Presvôts
AU - Adrien Meynard
PY - 2026
DA - 2026/09/15
PB - arXiv
DO - 10.48550/arxiv.2609.16796
UR - https://arxiv.org/abs/2609.16796
AB - Time-warping estimation is a fundamental problem in signal processing with applications in bioacoustics, radar, and biomedical analysis. This paper introduces a Time-Warping Estimation Trainable (TWET) model for estimating timewarping functions from a single observation. The proposed approach formulates time-warping estimation as a stationarization problem in the wavelet domain and leverages a hierarchical dilated convolutional architecture to estimate the time-warping functions. A differentiable stationarity criterion is introduced for end-to-end optimization. TWET is compared with existing approaches. Experimental results show improved deformation reconstruction accuracy together with significantly reduced computation time, making the framework compatible with low-latency applications.
ER -