This paper introduces Task 2 of the DCASE2019 Challenge, titled" Audio tagging with noisy
labels and minimal supervision". This task was hosted on the Kaggle platform as" Freesound …

An important problem in machine auditory perception is to recognize and detect sound
events. In this paper, we propose a sequential self-teaching approach to learning sounds …

The study of label noise in sound event recognition has recently gained attention with the
advent of larger and noisier datasets. This work addresses the problem of missing labels …

Recognizing ongoing events based on acoustic clues has been a critical yet challenging
problem that has attracted significant research attention in recent years. Joint audio-visual …

High quality labeled datasets have allowed deep learning to achieve impressive results on
many sound analysis tasks. Yet, it is labor-intensive to accurately annotate large amount of …

Weakly supervised learning algorithms are critical for scaling audio event detection to
several hundreds of sound categories. Such learning models should not only disambiguate …

In Weakly-supervised Sound Event Detection (WSED), the ground truth of training data
contains the presence or absence of each sound event only at the clip-level (ie, no frame …

The availability of audio data on sound sharing platforms such as Freesound gives users
access to large amounts of annotated audio. Utilising such data for training is becoming …

Label noise is emerging as a pressing issue in sound event classification. This arises as we
move towards larger datasets that are difficult to annotate manually, but it is even more …

The small-loss criterion is widely used in recent label-noise learning methods. However,
such a criterion only considers the loss of each training sample in a mini-batch but ignores …