Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping

by   Khaled Koutini, et al.

Deep Neural Networks are known to be very demanding in terms of computing and memory requirements. Due to the ever increasing use of embedded systems and mobile devices with a limited resource budget, designing low-complexity models without sacrificing too much of their predictive performance gained great importance. In this work, we investigate and compare several well-known methods to reduce the number of parameters in neural networks. We further put these into the context of a recent study on the effect of the Receptive Field (RF) on a model's performance, and empirically show that we can achieve high-performing low-complexity models by applying specific restrictions on the RFs, in combination with parameter reduction methods. Additionally, we propose a filter-damping technique for regularizing the RF of models, without altering their architecture and changing their parameter counts. We will show that incorporating this technique improves the performance in various low-complexity settings such as pruning and decomposed convolution. Using our proposed filter damping, we achieved the 1st rank at the DCASE-2020 Challenge in the task of Low-Complexity Acoustic Scene Classification.


page 1

page 2

page 3

page 4


Low-complexity CNNs for Acoustic Scene Classification

This paper presents a low-complexity framework for acoustic scene classi...

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

We propose a novel neural model compression strategy combining data augm...

TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene

Convolution neural networks (CNNs) have good performance in low-complexi...

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

In this paper, we present a robust and low complexity system for Acousti...

The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification

Convolutional Neural Networks (CNNs) have had great success in many mach...

Low-Complexity Steered Response Power Mapping based on Nyquist-Shannon Sampling

The steered response power (SRP) approach to acoustic source localizatio...

Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance

Minimal changes to neural architectures (e.g. changing a single hyperpar...

Please sign up or login with your details

Forgot password? Click here to reset