RCT: Random Consistency Training for Semi-supervised Sound Event Detection

21 Oct 2021  ·  Nian Shao, Erfan Loweimi, Xiaofei Li ·

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.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Sound Event Detection DESED RCT event-based F1 score 49.62 # 4
PSDS1 0.4395 # 3
PSDS2 0.6711 # 3