DocumentCode
2779880
Title
Research of speech recognition based on Auto-Correlated Corner approach
Author
Lu, Fei ; He, Wenxiu ; Chunyan
Author_Institution
Inst. of Intell. Inf. Syst., Zhejiang Univ. of Technol., Hangzhou, China
fYear
2009
fDate
17-19 June 2009
Firstpage
3203
Lastpage
3206
Abstract
Based on auto-correlated corner algorithm, we proposed a new method for pretreatment of speech signal in speech recognition system. The algorithm deleted semblable frames of speech signals which got after LPCC algorithm and MEL cepstrum transformation., and then solved characteristic redundancy efficiently. At last, we used speech recognition system based on spots-covering neural network to prove validity of auto-correlated corner algorithm.
Keywords
cepstral analysis; correlation methods; neural nets; speech recognition; LPCC algorithm; MEL cepstrum transformation; autocorrelated corner approach; speech recognition; speech signal; spots-covering neural network; Cepstrum; Educational institutions; Erbium; Helium; Hidden Markov models; Information systems; Intelligent systems; Neural networks; Speech recognition; Auto-Correlated Corner algorithm; MEL cepstrum transformation; neural network; speech recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Control and Decision Conference, 2009. CCDC '09. Chinese
Conference_Location
Guilin
Print_ISBN
978-1-4244-2722-2
Electronic_ISBN
978-1-4244-2723-9
Type
conf
DOI
10.1109/CCDC.2009.5191770
Filename
5191770
Link To Document