CNN-LTE: a Class of 1-X Pooling Convolutional Neural Networks on Label Tree Embeddings for Audio Scene Recognition

TL;DR

This paper presents CNN-LTE, a novel CNN architecture utilizing label tree embeddings for audio scene recognition, achieving high accuracy and outperforming baseline methods in the DCASE 2016 challenge.

Contribution

Introduction of CNN-LTE, a new CNN model that leverages label tree embeddings for improved audio scene recognition performance.

Findings

Achieved 81.2% and 83.3% recognition accuracy on development and test data.

Outperformed DCASE 2016 baseline by 8.7% and 6.1%.

Demonstrated effectiveness of label tree embeddings in CNNs for audio classification.

Abstract

We describe in this report our audio scene recognition system submitted to the DCASE 2016 challenge. Firstly, given the label set of the scenes, a label tree is automatically constructed. This category taxonomy is then used in the feature extraction step in which an audio scene instance is represented by a label tree embedding image. Different convolutional neural networks, which are tailored for the task at hand, are finally learned on top of the image features for scene recognition. Our system reaches an overall recognition accuracy of 81.2% and 83.3% and outperforms the DCASE 2016 baseline with absolute improvements of 8.7% and 6.1% on the development and test data, respectively.