Hodge and Podge: Hybrid Supervised Sound Event Detection with Multi-Hot MixMatch and Composition Consistence Training
arXiv:2002.06021
Abstract
In this paper, we propose a method called Hodge and Podge for sound event detection. We demonstrate Hodge and Podge on the dataset of Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 Challenge Task 4. This task aims to predict the presence or absence and the onset and offset times of sound events in home environments. Sound event detection is challenging due to the lack of large scale real strongly labeled data. Recently deep semi-supervised learning (SSL) has proven to be effective in modeling with weakly labeled and unlabeled data. This work explores how to extend deep SSL to result in a new, state-of-the-art sound event detection method called Hodge and Podge. With convolutional recurrent neural networks (CRNN) as the backbone network, first, a multi-scale squeeze-excitation mechanism is introduced and added to generate a pyramid squeeze-excitation CRNN. The pyramid squeeze-excitation layer can pay attention to the issue that different sound events have different durations, and to adaptively recalibrate channel-wise spectrogram responses. Further, in order to remedy the lack of real strongly labeled data problem, we propose multi-hot MixMatch and composition consistency training with temporal-frequency augmentation. Our experiments with the public DCASE2019 challenge task 4 validation data resulted in an event-based F-score of 43.4\%, and is about absolutely 1.6\% better than state-of-the-art methods in the challenge. While the F-score of the official baseline is 25.8\%.
arXiv commentarXiv admin note: substantial text overlap with arXiv:1907.07398
References in corpus (6)
- mixup: Beyond Empirical Risk Minimization
- Interpolation Consistency Training for Semi-Supervised Learning
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- Large-Scale Weakly Labeled Semi-Supervised Sound Event Detection in Domestic Environments
- DCASE 2018 Challenge Surrey Cross-Task convolutional neural network baseline
- HODGEPODGE: Sound event detection based on ensemble of semi-supervised learning methods