Unified Training of Feature Extractor and HMM Classifier for Speech Recognition

Cited 2 time in webofscience Cited 0 time in scopus
  • Hit : 283
  • Download : 0
We present a new unified training scheme using a feature extractor and HMM classifiers for better speech recognition performance. Both feature extractor and classifier are trained simultaneously to minimize classification error. Multiframe features are extracted using spectro-temporal dynamics and the feature extractor is implemented as a multilayer network, which is trained by a backpropagation (BP) algorithm with the help of an HMM inversion algorithm. The initial parameter values of the feature extractor are set for Mel-frequency cepstral coefficients (MFCC) as well as their delta and acceleration components. The experiments for phoneme classification demonstrate the practicality of unified training.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2012-02
Language
English
Article Type
Article
Citation

IEEE SIGNAL PROCESSING LETTERS, v.19, no.2, pp.111 - 114

ISSN
1070-9908
DOI
10.1109/LSP.2011.2179647
URI
http://hdl.handle.net/10203/101977
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 2 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0