Robust Sound Event Classification Using Deep Neural Networks

By Ian McLoughlin, Haomin Zhang, Zhipeng Xie, Yan Song, Wei Xiao. IEEE/ACM Transactions on Audio Speech and Language Processing, 2015

304 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.

SoundNet: Learning Sound Representations from Unlabeled Video (2016, background): “Even though there are unsupervised [20] and supervised [27, 23, 6, 12] deep learning methods applied to sound classification, the models are limited by the amount of available labeled natural sound data.”
SeCoST: Sequential Co-Supervision for Weakly Labeled Audio Event Detection (2019, background): “While several classical machine learning and deep learning methods have been developed for AED using strong labels [2], [1], [3], [4], much of the recent progress has focused on efficiently leveraging weakly labeled data [5].”
The Impact of Missing Labels and Overlapping Sound Events on Multi-label Multi-instance Learning for Sound Event Classification (2019, methodology): “Either the overlapping events are separated first using source separation methods [2, 3] or region extraction methods such as [4] prior to detection or the overlapping events are directly classified via a unifying classfication scheme [5, 6], with the latter being the most successful.”
Accelerating Mobile Audio Sensing Algorithms through On-Chip GPU Offloading (2017, unknown): “DNN keyword spotting [22], emotion recognition [30], speech recognition [33], sound event classification [49]”