Voice2Series: Reprogramming Acoustic Models for Time Series Classification
arXiv:2106.09296
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.
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
References in corpus (8)
- ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
- Kapre: On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with Keras
- A Two-Stage Approach to Device-Robust Acoustic Scene Classification
- Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation
- Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources
- A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning
- PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification
- Reprogramming Language Models for Molecular Representation Learning