English

Voice2Series: Reprogramming Acoustic Models for Time Series Classification

Machine Learning 2022-01-17 v3 Artificial Intelligence Neural and Evolutionary Computing Sound Audio and Speech Processing

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.

Keywords

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

R2 v1 2026-06-24T03:18:08.470Z