Top-down attention to complement independent component analysis for blind signal separation

Cited 6 time in webofscience Cited 0 time in scopus
  • Hit : 207
  • Download : 2
For robust speech recognition in real-world noisy environments, we present an algorithm to incorporate blind signal separation based on independent component analysis (ICA) and top-down attention processing. While ICA-based unmixing networks learn the inverse of mixing characteristics in frequency domain, their performance is limited by mismatches between the real-world mixing characteristics and assumptions of the ICA algorithm. The top-down process from a multiplayer Perceptron (MLP) classifier provides additional information on the speech signal, and fine-tunes the networks to compensate for the mismatches. For noisy speech signals recorded in a real office environment, the developed algorithm demonstrated great improvements on recognition performance. (C) 2002 Published by Elsevier Science B.V.
Publisher
ELSEVIER SCIENCE BV
Issue Date
2002-12
Language
English
Article Type
Article
Keywords

NEURAL NETWORKS; ALGORITHM

Citation

NEUROCOMPUTING, v.49, pp.315 - 327

ISSN
0925-2312
URI
http://hdl.handle.net/10203/10963
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 6 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0