Binaural semi-blind dereverberation of noisy convoluted speech signals

In order to overcome a limited performance of a conventional monaural model, this letter proposes a binaural blind dereverberation model. Its learning rule is derived using a blind least-squares measure by exploiting higher-order characteristics of output components. In order to prevent an unwanted whitening of speech signal, we adopt a semi-blind approach by employing a pre-determined whitening filter. The proposed model is evaluated using several simulated conditions and the results show better speech quality than those of the monaural model. The applicability of the model to the real environment is also shown by applying to real-recorded data. Especially, the proposed model attains much improved word error rates from 13.9 +/- 5.7(%) to 4.1 +/- 3.5(%) across 13 speakers for testing in the real speech recognition experiments. (c) 2008 Elsevier B.V. All rights reserved.
Publisher
ELSEVIER SCIENCE BV
Issue Date
2008-12
Language
ENG
Keywords

SOURCE SEPARATION; DECONVOLUTION; DECOMPOSITION; SYSTEMS

Citation

NEUROCOMPUTING, v.72, pp.636 - 642

ISSN
0925-2312
DOI
10.1016/j.neucom.2008.07.005
URI
http://hdl.handle.net/10203/9620
Appears in Collection
EE-Journal Papers(저널논문)
  • Hit : 167
  • Download : 1
  • Cited 0 times in thomson ci
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡClick to seewebofscience_button
⊙ Cited 2 items in WoSClick to see citing articles inrecords_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0