Discovering hierarchical speech features using convolutional non-negative matrix factorization

• Author: Sven Behnke

 
• Proceedings of International Joint Conference on Neural Networks (IJCNN), vol. 4, pp. 2758-2763, Portland, OR, July 2003.

 
• Abstract:
Discovering a representation that reflects the structure of a dataset is a first step for many inference and learning methods. This paper aims at finding a hierarchy of localized speech features that can be interpreted as parts.
Non-negative matrix factorization (NMF) has been proposed recently for the discovery of parts-based localized additive representations. Here, I propose a variant of this method, convolutional NMF, that enforces a particular local connectivity with shared weights. Analysis starts from a spectrogram. The hidden representations produced by convolutional NMF are input to the same analysis method at the next higher level.
Repeated application of convolutional NMF yields a sequence of increasingly abstract representations. These speech representations are parts-based, where complex higher-level parts are defined in terms of less complex lower-level ones.

 
• Full paper: ijcnn03.pdf