Secost: Sequential co-supervision for large scale weakly labeled audio event detection

Abstract

Weakly supervised learning algorithms are critical for scaling audio event detection to several hundreds of sound categories. Such learning models should not only disambiguate sound events efficiently with minimal class-specific annotation but also be robust to label noise, which is more apparent with weak labels instead of strong annotations. In this work, we propose a new framework for designing learning models with weak supervision by bridging ideas from sequential learning and knowledge distillation. We refer to the proposed methodology as SeCoST (pronounced Sequest) -- Sequential Co-supervision for training generations of Students. SeCoST incrementally builds a cascade of student-teacher pairs via a novel knowledge transfer method. Our evaluations on Audioset (the largest weakly labeled dataset available) show that SeCoST achieves a mean average precision of 0.383 while outperforming prior state of the art by a considerable margin.

arXiv commentAccepted IEEE ICASSP 2020

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Neural Machine Translation by Jointly Learning to Align and Translate
• Distilling the Knowledge in a Neural Network
• Do Deep Nets Really Need to be Deep?
• Born Again Neural Networks
• Audio Event Detection using Weakly Labeled Data
• Weakly Labelled AudioSet Tagging with Attention Neural Networks
• Multi-level Attention Model for Weakly Supervised Audio Classification
• A Closer Look at Weak Label Learning for Audio Events
• Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network

Cited by in corpus (3)

• Does Visual Self-Supervision Improve Learning of Speech Representations for Emotion Recognition?
• Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data
• A Joint Framework for Audio Tagging and Weakly Supervised Acoustic Event Detection Using DenseNet with Global Average Pooling