Non-negative matrix decomposition approaches to frequency domain analysis of music audio signals
On étudie l’application des algorithmes de décomposition matricielles tel que la Factorisation Matricielle Non-négative (FMN), aux représentations fréquentielles de signaux audio musicaux. Ces algorithmes, dirigés par une fonction d’erreur de reconstruction, apprennent un ensemble de fonctions de ba...
Main Author: | Wood, Sean |
---|---|
Other Authors: | Eck, Douglas |
Language: | en |
Published: |
2010
|
Subjects: | |
Online Access: | http://hdl.handle.net/1866/3769 |
Similar Items
-
Non-negative matrix decomposition approaches to frequency domain analysis of music audio signals
by: Wood, Sean
Published: (2010) -
Deep learning of representations and its application to computer vision
by: Goodfellow, Ian
Published: (2015) -
Designing Regularizers and Architectures for Recurrent Neural Networks
by: Krueger, David
Published: (2016) -
Recognition of Facial Expressions with Autoencoders and Convolutional-Nets
by: Almousli, Hani
Published: (2014) -
Recognition of Facial Expressions with Autoencoders and Convolutional-Nets
by: Almousli, Hani
Published: (2014)