Voice2Series: Reprogramming Acoustic Models for Time Series Classification
Abstract
Learning to classify time series with limited data is a practical yet challenging problem. Current methods are primarily based on hand-designed feature extraction rules or domain-specific data augmentation. Motivated by the advances in deep speech processing models and the fact that voice data are univariate temporal signals, in this paper, we propose Voice2Series (V2S), a novel end-to-end approach that reprograms acoustic models for time series classification, through input transformation learning and output label mapping. Leveraging the representation learning power of a large-scale pre-trained speech processing model, on 30 different time series tasks we show that V2S performs competitive results on 19 time series classification tasks. We further provide a theoretical justification of V2S by proving its population risk is upper bounded by the source risk and a Wasserstein distance accounting for feature alignment via reprogramming. Our results offer new and effective means to time series classification.
Cite
@article{arxiv.2106.09296,
title = {Voice2Series: Reprogramming Acoustic Models for Time Series Classification},
author = {Chao-Han Huck Yang and Yun-Yun Tsai and Pin-Yu Chen},
journal= {arXiv preprint arXiv:2106.09296},
year = {2022}
}
Comments
Updated version with a correction. The full draft was submitted in Jan 2021. The Voice2Series project initially was launched in Sep 2020. Accepted to ICML 2021, 16 Pages