Interpretable Super-Resolution via a Learned Time-Series Representation
arXiv:2006.07713
Abstract
We develop an interpretable and learnable Wigner-Ville distribution that produces a super-resolved quadratic signal representation for time-series analysis. Our approach has two main hallmarks. First, it interpolates between known time-frequency representations (TFRs) in that it can reach super-resolution with increased time and frequency resolution beyond what the Heisenberg uncertainty principle prescribes and thus beyond commonly employed TFRs, Second, it is interpretable thanks to an explicit low-dimensional and physical parameterization of the Wigner-Ville distribution. We demonstrate that our approach is able to learn highly adapted TFRs and is ready and able to tackle various large-scale classification tasks, where we reach state-of-the-art performance compared to baseline and learned TFRs.
References in corpus (6)
- STFT with Adaptive Window Width Based on the Chirp Rate
- A neural attention model for speech command recognition
- General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline
- Interpretable Convolutional Filters with SincNet
- Bottom-up Broadcast Neural Network For Music Genre Classification
- Learning Complex Basis Functions for Invariant Representations of Audio