Acoustic scene classification with RNN-LTE (Deep Recurrent Neural Networks with Label Tree Embedding) and CNN-LTE (1-max pooling Convolutional Neural Networks with Label Tree Embedding):

• Huy Phan, Philipp Koch, Lars Hertel, Marco Maass, Radoslaw Mazur, and Alfred Mertins. CNN-LTE: A Class of 1-X Pooling Convolutional Neural Networks on Label Tree Embeddings for Audio Scene Classification. In Proceedings of 42nd IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 136-140, 2017
• Huy Phan, Philipp Koch, Fabrice Katzberg, Marco Maass, Radoslaw Mazur, and Alfred Mertins. Audio Scene Classification with Deep Recurrent Neural Networks. In Proceedings of 18th Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 3043-3047, 2017
• Huy Phan, Lars Hertel, Marco Maass, Philipp Koch, Radoslaw Mazur, and Alfred Mertins. Improved Audio Scene Classification based on Label-Tree Embeddings and Convolutional Neural Networks. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP): 25(6), pp. 1278-1290, 2017

Matlab source of Label Tree Embedding (LTE) proposed in

• Huy Phan, Lars Hertel, Marco Maass, Philipp Koch, and Alfred Mertins. Label Tree Embeddings for Acoustic Scene Classification. In Proceedings of 24th ACM Multimedia (ACMMM), pp. 486-490, 2016

can be found at https://github.com/pquochuy/Label-Tree-Embedding