Urban Sound Classification : striving towards a fair comparison

Abstract

Urban sound classification has been achieving remarkable progress and is still an active research area in audio pattern recognition. In particular, it allows to monitor the noise pollution, which becomes a growing concern for large cities.The contribution of this paper is two-fold. First, we present our DCASE 2020 task 5 winning solution [31] which aims at helping the monitoring of urban noise pollution. It achieves a macro-AUPRC of 0.82 / 0.62 for the coarse / fine classification on validation set. Moreover, it reaches accuracies of 89.7% and 85.41% respectively on ESC-50 and US8k datasets.Second, it is not easy to find a fair comparison and to reproduce the performance of existing models. Sometimes authors copy-pasting the results of the original papers which is not helping reproducibility. As a result, we provide a fair comparison by using the same input representation, metrics and optimizer to assess performances. We preserve data augmentation used by the original papers. We hope this framework could help evaluate new architectures in this field.For better reproducibility, the code is available on our GitHub repository [35].

Improving Audio Classification Method by Combining Self-Supervision with Knowledge Distillation

“…Over the past few years, supervised audio classification methods have demonstrated excellent performance in various publicly available datasets [1,[3][4][5][6][7]. In the specific modeling process, supervised learning for audio classification assigns a discrete label or category to a segment of continuous audio information.…”

Learning spectro-temporal representations of complex sounds with parameterized neural networks

“…We reported the Mean, Min and Max of the Accuracy across the 10 folds. We used the code-base fromArnault et al (2020) for the training and evaluations of the 2 approaches. The topline approach is the use of a Mel-filterbanks with the CNN10 architecture fromKong et al (2020).…”