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
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;
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
DOI :
10.1109/CCDC.2009.5191770
