Cross-Referencing Self-Training Network for Sound Event Detection in Audio Mixtures

Abstract

Sound event detection is an important facet of audio tagging that aims to identify sounds of interest and define both the sound category and time boundaries for each sound event in a continuous recording. With advances in deep neural networks, there has been tremendous improvement in the performance of sound event detection systems, although at the expense of costly data collection and labeling efforts. In fact, current state-of-the-art methods employ supervised training methods that leverage large amounts of data samples and corresponding labels in order to facilitate identification of sound category and time stamps of events. As an alternative, the current study proposes a semi-supervised method for generating pseudo-labels from unsupervised data using a student-teacher scheme that balances self-training and cross-training. Additionally, this paper explores post-processing which extracts sound intervals from network prediction, for further improvement in sound event detection performance. The proposed approach is evaluated on sound event detection task for the DCASE2020 challenge. The results of these methods on both "validation" and "public evaluation" sets of DESED database show significant improvement compared to the state-of-the art systems in semi-supervised learning.

References in corpus (11)

• Distributed Representations of Words and Phrases and their Compositionality
• mixup: Beyond Empirical Risk Minimization
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Temporal Ensembling for Semi-Supervised Learning
• Interpolation Consistency Training for Semi-Supervised Learning
• Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
• Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
• Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
• Polyphonic Sound Event Detection by using Capsule Neural Networks
• Guided multi-branch learning systems for sound event detection with sound separation
• Polyphonic sound event detection based on convolutional recurrent neural networks with semi-supervised loss function for DCASE challenge 2020 task 4