auDeep is a Python toolkit for unsupervised feature learning with deep neural networks (DNNs). Currently, the main focus of this project is feature extraction from audio data with deep recurrent autoencoders. However, the core feature learning algorithms are not limited to audio data. Furthermore, we plan on implementing additional DNN-based feature learning approaches.

(c) 2019-2020 Shahin Amiriparian, Michael Freitag, Maurice Gerczuk, Sergey Pugachevskiy, Björn Schuller: Universität Augsburg

(c) 2017-2018 Michael Freitag, Shahin Amiriparian, Maurice Gerczuk, Sergey Pugachevskiy, Nicholas Cummins, Björn Schuller: Universität Passau Published under GPLv3, see the LICENSE.md file for details.

Please direct any questions or requests to Shahin Amiriparian (shahin.amiriparian at tum.de) or Michael Freitag (freitagm at fim.uni-passau.de).

Citing

If you use auDeep or any code from auDeep in your research work, you are kindly asked to acknowledge the use of auDeep in your publications.

S. Amiriparian, M. Freitag, N. Cummins, and B. Schuller. Sequence to sequence autoencoders for unsupervised representation learning from audio, Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop, pp. 17-21, 2017

M. Freitag, S. Amiriparian, S. Pugachevskiy, N. Cummins, and B. Schuller, “auDeep: Unsupervised Learning of Representations from Audio with Deep Recurrent Neural Networks,” Journal of Machine Learning Research, vol. 18, no. 173, pp. 1–5, 2018