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
back
to selected multimodal communication and speech processing publications