Wider or Deeper Neural Network Architecture for Acoustic Scene Classification with Mismatched Recording Devices

TL;DR

This paper introduces a low-complexity acoustic scene classification system using a novel inception-residual network, ensemble techniques, and channel reduction, achieving competitive accuracy on a benchmark dataset suitable for edge devices.

Contribution

The paper proposes a new inception-residual network architecture combined with ensemble and channel reduction techniques for robust, low-complexity acoustic scene classification.

Findings

Achieved 69.9% accuracy on DCASE 2020 dataset.

Model complexity is 2.4 million parameters, suitable for edge devices.

Competitive performance compared to state-of-the-art systems.

Abstract

In this paper, we present a robust and low complexity system for Acoustic Scene Classification (ASC), the task of identifying the scene of an audio recording. We first construct an ASC baseline system in which a novel inception-residual-based network architecture is proposed to deal with the mismatched recording device issue. To further improve the performance but still satisfy the low complexity model, we apply two techniques: ensemble of multiple spectrograms and channel reduction on the ASC baseline system. By conducting extensive experiments on the benchmark DCASE 2020 Task 1A Development dataset, we achieve the best model performing an accuracy of 69.9% and a low complexity of 2.4M trainable parameters, which is competitive to the state-of-the-art ASC systems and potential for real-life applications on edge devices.