Sorry, you need to enable JavaScript to visit this website.

A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling

Citation Author(s):
Yun Wang, Juncheng Li, Florian Metze
Submitted by:
Yun Wang
Last updated:
9 May 2019 - 12:55pm
Document Type:
Presentation Slides
Document Year:
Juncheng Li
Paper Code:


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.

0 users have voted:


2019.05 Slides for ICASSP.pdf