Acoustic scene classification using multi-layer temporal pooling based on convolutional neural network
This work addresses acoustic scene classification for audio analysis applications, but it is incremental as it builds on existing CNN and SVM methods.
The paper tackled acoustic scene classification by proposing a multi-layer temporal pooling method to capture temporal dynamics in audio signals, achieving 75.28% accuracy on the DCASE 2018 task 1 development dataset.
The performance of an Acoustic Scene Classification (ASC) system is highly depending on the latent temporal dynamics of the audio signal. In this paper, we proposed a multiple layers temporal pooling method using CNN feature sequence as in-put, which can effectively capture the temporal dynamics for an entire audio signal with arbitrary duration by building direct connections between the sequence and its time indexes. We applied our novel framework on DCASE 2018 task 1, ASC. For evaluation, we trained a Support Vector Machine (SVM) with the proposed Multi-Layered Temporal Pooling (MLTP) learned features. Experimental results on the development dataset, usage of the MLTP features significantly improved the ASC performance. The best performance with 75.28% accuracy was achieved by using the optimal setting found in our experiments.