Change search
ReferencesLink to record
Permanent link

Direct link
Learning Speech Features in the Presence of Noise: Sparse Convolutive Robust Non-Negative Matrix Factorisation
Complex and Adaptive Systems Laboratory, University College Dublin, Ireland.ORCID iD: 0000-0002-3912-1470
Complex and Adaptive Systems Laboratory, University College Dublin, Ireland.
2009 (English)In: 16th International Conference on Digital Signal Processing / [ed] IEEE, Santorini, Greece: IEEE Press, 2009, 1-6 p.Conference paper (Refereed)
Abstract [en]

We introduce a non-negative matrix factorization technique which learns speech features with temporal extent in the presence of non-stationary noise. Our proposed technique, namely Sparse convolutive robust non-negative matrix factorization, is robust in the presence of noise due to our explicit treatment of noise as an interfering source in the factorization. We derive multiplicative update rules using the alpha divergence objective. We show that our proposed method yields superior performance to sparse convolutive non-negative matrix factorization in a feature learning task on noisy data and comparable results to dedicated speech enhancement techniques.

Place, publisher, year, edition, pages
Santorini, Greece: IEEE Press, 2009. 1-6 p.
Keyword [en]
Spectral factorization, Speech enhancement
National Category
Signal Processing
Research subject
Applied and Computational Mathematics
URN: urn:nbn:se:kth:diva-175437DOI: 10.1109/ICDSP.2009.5201068ScopusID: 2-s2.0-70449553294ISBN: 978-1-4244-3297-4OAI: diva2:860973

QC 20151211

Available from: 2015-10-14 Created: 2015-10-14 Last updated: 2015-12-11Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
de Fréin, Ruairí
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 6 hits
ReferencesLink to record
Permanent link

Direct link