Receptive-field-regularized CNN variants for acoustic scene classification (2019-09-05T00:00:00.000000Z)

TL;DR

This paper performs a systematic investigation of different RF configuration for various CNN architectures on the DCASE 2019 Task 1.A dataset, introduces Frequency Aware CNNs to compensate for the lack of frequency information caused by the restricted RF, and investigates if and in what RF ranges they yield additional improvement.

Abstract

Acoustic scene classification and related tasks have been dominated by Convolutional Neural Networks (CNNs). Top-performing CNNs use mainly audio spectograms as input and borrow their architectural design primarily from computer vision. A recent study has shown that restricting the receptive field (RF) of CNNs in appropriate ways is crucial for their performance, robustness and generalization in audio tasks. One side effect of restricting the RF of CNNs is that more frequency information is lost. In this paper, we perform a systematic investigation of different RF configuration for various CNN architectures on the DCASE 2019 Task 1.A dataset. Second, we introduce Frequency Aware CNNs to compensate for the lack of frequency information caused by the restricted RF, and experimentally determine if and in what RF ranges they yield additional improvement. The result of these investigations are several well-performing submissions to different tasks in the DCASE 2019 Challenge.

Authors

Hamid Eghbalzadeh

4 papers

G. Widmer

7 papers

Khaled Koutini

3 papers

Receptive-field-regularized CNN variants for acoustic scene classification

TL;DR

Abstract

Authors

References25 items

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

Audio tagging with noisy labels and minimal supervision

Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet

Normalization Before Shaking Toward Learning Symmetrically Distributed Representation Without Margin in Speech Emotion Recognition

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

Dynamic Routing Between Capsules

mixup: Beyond Empirical Risk Minimization

Shake-Shake regularization

Understanding the Effective Receptive Field in Deep Convolutional Neural Networks

CNN architectures for large-scale audio classification

Densely Connected Convolutional Networks

Identity Mappings in Deep Residual Networks

Deep Residual Learning for Image Recognition

Detection and Classification of Acoustic Scenes and Events

Adam: A Method for Stochastic Optimization

Acoustic Scene Classification in DCASE 2019 Challenge: Closed and Open Set Classification and Data Mismatch Setups

“Acoustic scene classiﬁcation and audio tagging with receptive-ﬁeld-regularized CNNs,”

ACOUSTIC SCENE CLASSIFICATION WITH FULLY CONVOLUTIONAL NEURAL NETWORKS AND I-VECTORS Technical Report

Training general-purpose audio tagging networks with noisy labels and iterative self-verification

STACKED CONVOLUTIONAL NEURAL NETWORKS FOR GENERAL-PURPOSE AUDIO TAGGING Technical Report

Iterative knowledge distillation in R-CNNs for weakly-labeled semi-supervised sound event detection

“Acoustic scene classiﬁcation by ensemble of spectrograms based on adaptive temporal divisions.”

Ensemble of Convolutional Neural Networks for Weakly-supervised Sound Event Detection Using Multiple Scale Input

CLASSIFYING SHORT ACOUSTIC SCENES WITH I-VECTORS AND CNNS : CHALLENGES AND OPTIMISATIONS FOR THE 2017 DCASE ASC TASK

CP-JKU SUBMISSIONS FOR DCASE-2016 : A HYBRID APPROACH USING BINAURAL I-VECTORS AND DEEP CONVOLUTIONAL NEURAL NETWORKS

Field of Study

Venue Information

Name

Type

URL

Alternate Names