Voice2Series: Reprogramming Acoustic Models for Time Series Classification (2021-06-17T00:00:00.000000Z)

TL;DR

Voice2Series (V2S) is proposed, a novel end-to-end approach that reprograms acoustic models for time series classification, through input transformation learning and output label mapping and it is shown that V2S performs competitive results on 19 time series Classification tasks.

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.

Authors

Chao-Han Huck Yang

6 papers

Pin-Yu Chen

17 papers

Yun-Yun Tsai

2 papers

TL;DR

Abstract

Authors

References61 items

PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification

WARP: Word-level Adversarial ReProgramming

Reprogramming Language Models for Molecular Representation Learning

A Two-Stage Approach to Device-Robust Acoustic Scene Classification

Fast and Accurate Time Series Classification Through Supervised Interval Search

Decentralizing Feature Extraction with Quantum Convolutional Neural Network for Automatic Speech Recognition

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: Principals, Recent Advances, and Applications

Acoustic Scene Classification in DCASE 2020 Challenge: Generalization Across Devices and Low Complexity Solutions

Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement

MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals

Look, Listen, and Learn More: Design Choices for Deep Audio Embeddings

ConvTimeNet: A Pre-trained Deep Convolutional Neural Network for Time Series Classification

Enhancing Sound Texture in CNN-based Acoustic Scene Classification

Transfer learning for time series classification

The UCR time series archive

Deep learning for time series classification: a review

Adversarial Reprogramming of Text Classification Neural Networks

A novel transfer learning framework for time series forecasting

A neural attention model for speech command recognition

Adversarial Reprogramming of Neural Networks

Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition

Computational Optimal Transport

MobileNetV2: Inverted Residuals and Linear Bottlenecks

Sliced Wasserstein Distance for Learning Gaussian Mixture Models

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

On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning

English Conversational Telephone Speech Recognition by Humans and Machines

Audio Set: An ontology and human-labeled dataset for audio events

How is visual salience computed in the brain? Insights from behaviour, neurobiology and modelling

Modelling auditory attention

Time series classification from scratch with deep neural networks: A strong baseline

CNN architectures for large-scale audio classification

Temporal Convolutional Networks: A Unified Approach to Action Segmentation

Learning Deep Features for Discriminative Localization

Deep Residual Learning for Image Recognition

The BOSS is concerned with time series classification in the presence of noise

ESC: Dataset for Environmental Sound Classification

Time-Series Classification with COTE: The Collective of Transformation-Based Ensembles

Adam: A Method for Stochastic Optimization

Fully convolutional networks for semantic segmentation

Very Deep Convolutional Networks for Large-Scale Image Recognition

A review of unsupervised feature learning and deep learning for time-series modeling

Predictive modelling of bone ageing

Classification of time series by shapelet transformation

A shapelet transform for time series classification

Time Series Classification Using Support Vector Machine with Gaussian Elastic Metric Kernel

Heartbeat Time Series Classification With Support Vector Machines

Auditory attention : focusing the searchlight on sound

Three Myths about Dynamic Time Warping Data Mining

Pattern Extraction for Time Series Classification

Use of Fourier transform infrared spectroscopy and partial least squares regression for the detection of adulteration of strawberry purées

Voice2Series: Reprogramming Acoustic Models for Time Series Classification

Reprogramming of neural networks: A new and improved machine learning technique

A Regression Approach to Speech Enhancement Based on Deep Neural Networks

A Shapelet Transform for Time Series Classification

Visualizing Data using t-SNE

On a space of completely additive functions

This Paper Is Included in the Proceedings of the 12th Usenix Symposium on Operating Systems Design and Implementation (osdi '16). Tensorflow: a System for Large-scale Machine Learning Tensorflow: a System for Large-scale Machine Learning

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names