Noise-robust speech recognition using top-down selective attention with an HMM classifier

Cited 13 time in webofscience Cited 16 time in scopus
  • Hit : 682
  • Download : 721
For noise-robust speech recognition, we incorporated a top-down attention mechanism into a hidden Markov model classifier with Mel-frequency cepstral coefficient features. The attention filter was introduced at the outputs of the Mel-scale filterbank and adjusted to maximize the log-likelihood of the attended features with the attended class. A low-complexity constraint was proposed to prevent the attention filter from over-fitting' and a confidence measure was introduced on the attention. A classification was made to the class with the maximum confidence measure, and demonstrated 54 % and 68 % reduction of the false recognition rate with 15-and 20-dB signal-to-noise ratio, respectively.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2007-07
Language
English
Article Type
Article
Keywords

MODEL

Citation

IEEE SIGNAL PROCESSING LETTERS, v.14, pp.489 - 491

ISSN
1070-9908
DOI
10.1109/LSP.2006.891326
URI
http://hdl.handle.net/10203/10215
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
000247407000015.pdf(115.39 kB)Download
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 13 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0