auDeep: Unsupervised Learning of Representations from Audio with Deep Recurrent Neural Networks

auDeep is a Python toolkit for deep unsupervised representation learning from data. It is based on a recurrent sequence to sequence autoencoder which can learn representations of time series data by taking into their temporal dynamics. We provide an extensive command line interface addition to a Python API for users and developers, both of which are documented and publicly available at://github.com/auDeep/auDeep. Experimental results indicate that auDeep are competitive with state-of-the art audio classification.