Skip to Main content Skip to Navigation

Foveal autoregressive neural time-series modeling

Abstract : This dissertation studies unsupervised time-series modelling. We first focus on the problem of linearly predicting future values of a time-series under the assumption of long-range dependencies, which requires to take into account a large past. We introduce a family of causal and foveal wavelets which project past values on a subspace which is adapted to the problem, thereby reducing the variance of the associated estimators. We then investigate under which conditions non-linear predictors exhibit better performances than linear ones. Time-series which admit a sparse time-frequency representation, such as audio ones, satisfy those requirements, and we propose a prediction algorithm using such a representation. The last problem we tackle is audio time-series synthesis. We propose a new generation method relying on a deep convolutional neural network, with an encoder-decoder architecture, which allows to synthesize new realistic signals. Contrary to state-of-the-art methods, we explicitly use time-frequency properties of sounds to define an encoder with the scattering transform, while the decoder is trained to solve an inverse problem in an adapted metric.
Complete list of metadata
Contributor : ABES STAR :  Contact
Submitted on : Wednesday, September 8, 2021 - 3:44:10 PM
Last modification on : Friday, June 24, 2022 - 3:28:47 AM
Long-term archiving on: : Friday, December 10, 2021 - 9:55:18 AM


Version validated by the jury (STAR)


  • HAL Id : tel-03338394, version 1



Mathieu Andreux. Foveal autoregressive neural time-series modeling. Neural and Evolutionary Computing [cs.NE]. Université Paris sciences et lettres, 2018. English. ⟨NNT : 2018PSLEE073⟩. ⟨tel-03338394⟩



Record views


Files downloads