SeCoST: Sequential Co-Supervision for Weakly Labeled Audio Event Detection

By Anurag Kumar, Vamsi Krishna Ithapu. 2019

11 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Eduardo Fonseca
2. Xavier Serra
3. Manoj Plakal
4. Xingjun Ma
5. D. Ellis
6. Aren Jansen
7. Xavier Favory
8. Yisen Wang

Citations in the corpus

• Addressing Missing Labels in Large-Scale Sound Event Recognition Using a Teacher-Student Framework With Loss Masking (2020, background): “Previous work analyses the impact of label noise in these tasks [9, 10], as well as proposes ways to mitigate its negative effect [11, 12, 13, 14].”
• Large Scale Audiovisual Learning of Sounds with Weakly Labeled Data (2020, methodology): “Most of the recent methods rely on deep neural networks, in particular, deep Convolutional Neural Networks (ConvNets) [Kumar and Ithapu, 2020; Adavanne et al., 2019; Kong et al., 2019; Ford et al., 2019].”
• Normalized Loss Functions for Deep Learning with Noisy Labels (2020, methodology): “SeCoST extends MentorNet to a cascade of student-teacher pairs via a knowledge transfer method (Kumar & Ithapu, 2019).”