A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification

TL;DR

This paper introduces Acoustic Lottery, a framework that uses the Lottery Ticket Hypothesis to compress neural models for device-robust acoustic scene classification, achieving high accuracy with significantly reduced model size.

Contribution

It presents a novel combination of data augmentation, knowledge transfer, pruning, and quantization based on LTH for low-resource, multi-device ASC.

Findings

Model compression up to 10,000 times while maintaining accuracy

Achieved 79.4% validation accuracy and 0.64 Log loss

Effective for low-resource, multi-device acoustic scene classification

Abstract

We propose a novel neural model compression strategy combining data augmentation, knowledge transfer, pruning, and quantization for device-robust acoustic scene classification (ASC). Specifically, we tackle the ASC task in a low-resource environment leveraging a recently proposed advanced neural network pruning mechanism, namely Lottery Ticket Hypothesis (LTH), to find a sub-network neural model associated with a small amount non-zero model parameters. The effectiveness of LTH for low-complexity acoustic modeling is assessed by investigating various data augmentation and compression schemes, and we report an efficient joint framework for low-complexity multi-device ASC, called \emph{Acoustic Lottery}. Acoustic Lottery could compress an ASC model up to $1/10^{4}$ and attain a superior performance (validation accuracy of 79.4% and Log loss of 0.64) compared to its not compressed seed model. All results reported in this work are based on a joint effort of four groups, namely GT-USTC-UKE-Tencent, aiming to address the "Low-Complexity Acoustic Scene Classification (ASC) with Multiple Devices" in the DCASE 2021 Challenge Task 1a.