Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification

Abstract

The ability of deep convolutional neural networks (CNN) to learn discriminative spectro-temporal patterns makes them well suited to environmental sound classification. However, the relative scarcity of labeled data has impeded the exploitation of this family of high-capacity models. This study has two primary contributions: first, we propose a deep convolutional neural network architecture for environmental sound classification. Second, we propose the use of audio data augmentation for overcoming the problem of data scarcity and explore the influence of different augmentations on the performance of the proposed CNN architecture. Combined with data augmentation, the proposed model produces state-of-the-art results for environmental sound classification. We show that the improved performance stems from the combination of a deep, high-capacity model and an augmented training set: this combination outperforms both the proposed CNN without augmentation and a "shallow" dictionary learning model with augmentation. Finally, we examine the influence of each augmentation on the model's classification accuracy for each class, and observe that the accuracy for each class is influenced differently by each augmentation, suggesting that the performance of the model could be improved further by applying class-conditional data augmentation.

Accepted November 2016, IEEE Signal Processing Letters. Copyright IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material, creating new collective works, for resale or redistribution, or reuse of any copyrighted component of this work in other works

References in corpus (2)

• Recurrent Neural Networks for Polyphonic Sound Event Detection in Real Life Recordings
• Automatic Environmental Sound Recognition: Performance versus Computational Cost

Cited by in corpus (43)

• Regularized Deep Networks in Intelligent Transportation Systems: A Taxonomy and a Case Study
• A scoping review of transfer learning research on medical image analysis using ImageNet
• Automatic acoustic detection of birds through deep learning: the first Bird Audio Detection challenge
• A Survey of Sound Source Localization with Deep Learning Methods
• An evidential classifier based on Dempster-Shafer theory and deep learning
• Robust sound event detection in bioacoustic sensor networks
• Polyphonic Sound Event Detection and Localization using a Two-Stage Strategy
• An Ensemble of Convolutional Neural Networks for Audio Classification
• Convolutional Neural Networks for Automatic Meter Reading
• Physics-Driven Regularization of Deep Neural Networks for Enhanced Engineering Design and Analysis
• Audio-Based Activities of Daily Living (ADL) Recognition with Large-Scale Acoustic Embeddings from Online Videos
• Automatic COVID-19 disease diagnosis using 1D convolutional neural network and augmentation with human respiratory sound based on parameters: cough, breath, and voice
• Joint Time-Frequency Scattering
• Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks
• SALSA: Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detection
• Polyphonic Sound Event Detection by using Capsule Neural Networks
• Compact recurrent neural networks for acoustic event detection on low-energy low-complexity platforms
• Multiscale CNN based Deep Metric Learning for Bioacoustic Classification: Overcoming Training Data Scarcity Using Dynamic Triplet Loss
• The life of a New York City noise sensor network
• A Sequence Matching Network for Polyphonic Sound Event Localization and Detection
• Hearing What You Cannot See: Acoustic Vehicle Detection Around Corners
• Scene-Aware Audio Rendering via Deep Acoustic Analysis
• Texture Selection for Automatic Music Genre Classification
• CAA-Net: Conditional Atrous CNNs with Attention for Explainable Device-robust Acoustic Scene Classification
• Cost-effective On-device Continual Learning over Memory Hierarchy with Miro
• Applying Visual Domain Style Transfer and Texture Synthesis Techniques to Audio - Insights and Challenges
• 1-Dimensional polynomial neural networks for audio signal related problems
• Multimodal Urban Sound Tagging with Spatiotemporal Context
• MLGaze: Machine Learning-Based Analysis of Gaze Error Patterns in Consumer Eye Tracking Systems
• Masked Conditional Neural Networks for Environmental Sound Classification
• Learning spectro-temporal representations of complex sounds with parameterized neural networks
• Advancing Multi-grained Alignment for Contrastive Language-Audio Pre-training
• A Systematic Evaluation of Adversarial Attacks against Speech Emotion Recognition Models
• Music Genre Classification using Masked Conditional Neural Networks
• Environmental Sound Recognition using Masked Conditional Neural Networks
• Spatial mixup: Directional loudness modification as data augmentation for sound event localization and detection
• In-filter Computing For Designing Ultra-light Acoustic Pattern Recognizers
• Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems
• An evaluation of CNN models and data augmentation techniques in hierarchical localization of mobile robots
• From Physics to Representation: Audio Learning with Synthetic Pre-training via Procedural Generation
• Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization
• Investigation into respiratory sound classification for an imbalanced data set using hybrid LSTM-KAN architectures
• Learning Music Audio Representations With Limited Data