Institutions | About Us | Help | Gaeilge
rian logo

Go Back
Discovering Convolutive Speech Phones Using Sparseness and Non-negativity
O'Grady, Paul D.; Pearlmutter, Barak A.
Discovering a representation that allows auditory data to be parsimoniously represented is useful for many machine learning and signal processing tasks. Such a representation can be constructed by Non-negative Matrix Factorisation (NMF), which is a method for finding parts-based representations of non-negative data. Here, we present a convolutive NMF algorithm that includes a sparseness constraint on the activations and has multiplicative updates. In combination with a spectral magnitude transform of speech, this method extracts speech phones that exhibit sparse activation patterns, which we use in a supervised separation scheme for monophonic mixtures.
Keyword(s): Separation Performance; Positive Matrix Factorization; Sparseness Constraint; Female Speaker; Reconstruction Objective
Publication Date:
Type: Book chapter
Peer-Reviewed: Yes
Institution: Maynooth University
Citation(s): O'Grady, Paul D. and Pearlmutter, Barak A. (2007) Discovering Convolutive Speech Phones Using Sparseness and Non-negativity. In: ICA 2007: Independent Component Analysis and Signal Separation. Lecture Notes in Computer Science book series (LNCS) (4666). Springer, pp. 520-527. ISBN 9783540744948
Publisher(s): Springer
File Format(s): other
Related Link(s):
First Indexed: 2018-11-28 06:00:30 Last Updated: 2018-11-28 06:00:30