A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling
Authors:
Top Cited Papers
- 1 May 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 31-35
Abstract
Sound event detection (SED) entails two subtasks: recognizing what types of sound events are present in an audio stream (audio tagging), and pinpointing their onset and offset times (localization). In the popular multiple instance learning (MIL) framework for SED with weak labeling, an important component is the pooling function. This paper compares five types of pooling functions both theoretically and experimentally, with special focus on their performance of localization. Although the attention pooling function is currently receiving the most attention, we find the linear softmax pooling function to perform the best among the five. Using this pooling function, we build a neural network called TALNet. It is the first system to reach state-of-the-art audio tagging performance on Audio Set, while exhibiting strong localization performance on the DCASE 2017 challenge at the same time.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Convolutional Recurrent Neural Networks for Polyphonic Sound Event DetectionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017
- Audio Set: An ontology and human-labeled dataset for audio events2017
- CNN architectures for large-scale audio classification2017
- Audio Event Detection using Weakly Labeled Data2016
- Metrics for Polyphonic Sound Event DetectionApplied Sciences, 2016
- Audio-based multimedia event detection using deep recurrent neural networks2016
- Recurrent neural networks for polyphonic sound event detection in real life recordings2016
- Exploiting spectro-temporal locality in deep learning based acoustic event detectionEURASIP Journal on Audio, Speech, and Music Processing, 2015
- XSEDE: Accelerating Scientific DiscoveryComputing in Science & Engineering, 2014
- Multiple instance classification: Review, taxonomy and comparative studyArtificial Intelligence, 2013