Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data

2019/03/29 by Zixing Zhang, Zhang, Zixing, Jing Han +9 · 2 citations
Computer Science · Engineering · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #cs.LG #cs.SD #eess.AS #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1903.12422

accepted by IEEE JBHI

arxiv created 2019/03/29 · openalex publication_date 2019/03/29 · arxiv updated 2019/04/01 · openalex created_date 2019/04/11 · openalex updated_date 2026/07/28

Abstract

One of the frontier issues that severely hamper the development of automatic snore sound classification (ASSC) associates to the lack of sufficient supervised training data. To cope with this problem, we propose a novel data augmentation approach based on semi-supervised conditional Generative Adversarial Networks (scGANs), which aims to automatically learn a mapping strategy from a random noise space to original data distribution. The proposed approach has the capability of well synthesizing 'realistic' high-dimensional data, while requiring no additional annotation process. To handle the mode collapse problem of GANs, we further introduce an ensemble strategy to enhance the diversity of the generated data. The systematic experiments conducted on a widely used Munich-Passau snore sound corpus demonstrate that the scGANs-based systems can remarkably outperform other classic data augmentation systems, and are also competitive to other recently reported systems for ASSC.

Citations

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Improved Techniques for Training GANs
• Unrolled Generative Adversarial Networks
• AdaGAN: Boosting Generative Models
• Language Generation with Recurrent Generative Adversarial Networks without Pre-training
• Learning audio sequence representations for acoustic event classification
• Semi-supervised Conditional GANs
• Generative Adversarial Networks: An Overview
• Data Augmentation in Emotion Classification Using Generative Adversarial Networks
• Data Augmentation Generative Adversarial Networks
• Learning to Fuse Music Genres with Generative Adversarial Dual Learning
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Cited by

• Generative Artificial Intelligence for Air Shower Simulation
• Generative adversarial networks in time series: A survey and taxonomy

Related

• EnvGAN: Adversarial Synthesis of Environmental Sounds for Data Augmentation
• Deep Learning Features for Robust Detection of Acoustic Events in Sleep-Disordered Breathing
• Data Augmentation of Room Classifiers using Generative Adversarial Networks
• Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance
• Generative AI-based data augmentation for improved bioacoustic classification in noisy environments