# Classifying Variable-Length Audio Files with All-Convolutional Networks and Masked Global Pooling

arXiv: https://arxiv.org/abs/1607.02857 · HTML: https://mlsanity.com/paper/1607.02857/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2016.

## Built on by (most cited first, 2 of 2)

- [Convolutional Neural Networks for Time-dependent Classification of Variable-length Time Series](https://mlsanity.com/paper/2207.03718/) (2022)
- [Music Genre Classification with ResNet and Bi-GRU Using Visual Spectrograms](https://mlsanity.com/paper/2307.10773/) (2023)

## Abstract (arXiv)

We trained a deep all-convolutional neural network with masked global pooling to perform single-label classification for acoustic scene classification and multi-label classification for domestic audio tagging in the DCASE-2016 contest. Our network achieved an average accuracy of 84.5% on the four-fold cross-validation for acoustic scene recognition, compared to the provided baseline of 72.5%, and an average equal error rate of 0.17 for domestic audio tagging, compared to the baseline of 0.21. The network therefore improves the baselines by a relative amount of 17% and 19%, respectively. The network only consists of convolutional layers to extract features from the short-time Fourier transform and one global pooling layer to combine those features. It particularly possesses neither fully-connected layers, besides the fully-connected output layer, nor dropout layers.