Audio Scene Classification with Deep Recurrent Neural Networks

Understand

We introduce in this work an efficient approach for audio scene classification using deep recurrent neural networks.

• An audio scene is firstly transformed into a sequence of high-level label tree embedding feature vectors.
• The vector sequence is then divided into multiple subsequences on which a deep GRU-based recurrent neural network is trained for sequence-to-label classification.
• The global predicted label for the entire sequence is finally obtained via aggregation of subsequence classification outputs.