RCT: Random Consistency Training for Semi-supervised Sound Event Detection
arXiv:2110.11144
Abstract
Sound event detection (SED), as a core module of acoustic environmental analysis, suffers from the problem of data deficiency. The integration of semi-supervised learning (SSL) largely mitigates such problem while bringing no extra annotation budget. This paper researches on several core modules of SSL, and introduces a random consistency training (RCT) strategy. First, a self-consistency loss is proposed to fuse with the teacher-student model to stabilize the training. Second, a hard mixup data augmentation is proposed to account for the additive property of sounds. Third, a random augmentation scheme is applied to flexibly combine different types of data augmentations. Experiments show that the proposed strategy outperform other widely-used strategies.
arXiv commentPreprint for interspeech 2022
References in corpus (8)
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Interpolation Consistency Training for Semi-Supervised Learning
- Learning with Pseudo-Ensembles
- Learnable pooling with Context Gating for video classification
- Learning from Between-class Examples for Deep Sound Recognition
- Heavily Augmented Sound Event Detection utilizing Weak Predictions
- Self-training with noisy student model and semi-supervised loss function for dcase 2021 challenge task 4