Sound Event Detection by Consistency Training and Pseudo-Labeling With Feature-Pyramid Convolutional Recurrent Neural Networks
Authors:
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 376-380
Abstract
Due to the high cost of large-scale strong labeling, sound event detection (SED) using only weakly-labeled and unlabeled data has drawn increasing attention in recent years. To exploit large amount of unlabeled in-domain data efficiently, we applied three semi-supervised learning strategies: interpolation consistency training (ICT), shift consistency training (SCT), and weakly pseudo-labeling. In addition, we propose FP-CRNN, a convolutional recurrent neural network (CRNN) which contains feature-pyramid (FP) components, to leverage temporal information by utilizing features at different scales. Experiments were conducted on DCASE 2020 task 4. In terms of event-based F-measure, these approaches outperform the official baseline system, at 34.8%, with the highest F-measure of 48.0% achieved by an FP-CRNN that was trained with the combination of all three strategies.Keywords
This publication has 12 references indexed in Scilit:
- Interpolation Consistency Training for Semi-supervised Learning2019
- HODGEPODGE: Sound Event Detection Based on Ensemble of Semi-Supervised Learning Methods2019
- Large-Scale Weakly Supervised Audio Classification Using Gated Convolutional Neural Network2018
- Duration-Controlled LSTM for Polyphonic Sound Event DetectionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017
- Feature Pyramid Networks for Object Detection2017
- Convolutional Recurrent Neural Networks for Polyphonic Sound Event DetectionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017
- Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Recognition2016
- Deep Residual Learning for Image Recognition2016
- Monitoring Activities of Daily Living in Smart Homes: Understanding human behaviorIEEE Signal Processing Magazine, 2016
- A Method for Automatic Fall Detection of Elderly People Using Floor Vibrations and Sound—Proof of Concept on Human Mimicking Doll FallsIEEE Transactions on Biomedical Engineering, 2009