Search

Your search keyword '"Recurrent Neural Net-works"' showing total 1 results
Start Over Descriptor "Recurrent Neural Net-works" Topic audio processing
1 results on '"Recurrent Neural Net-works"'

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

Author

Freitag, Michael, Amiriparian, Shahin, Pugachevskiy, Sergey, Cummins, Nicholas, and Schuller, Björn

Subjects
*SUPERVISED learning, *REPRESENTATION theory, *ARTIFICIAL neural networks, *MATHEMATICAL sequences, *PYTHON programming language, *TIME series analysis
Abstract

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

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results