Title :
Wavelet-based feature extraction of speech signal for cochlear implants
Author :
Nie, Kaibao ; Lan, Ning ; Gao, Shangkai
Author_Institution :
Dept. of Electron. Eng., Shandong Univ., Jinan, China
Abstract :
Presents a wavelet-based method used in the feature extraction of speech signals in order to generate stimulation parameters for cochlear implants. This method can provide both envelope signals in each band and tonal patterns for some languages, such as Chinese. Results show that wavelet-based speech analysis is capable of performing speech signal processing for cochlear implants
Keywords :
ear; feature extraction; hearing aids; prosthetics; speech processing; wavelet transforms; Chinese; cochlear implants; envelope signals; stimulation parameters generation; tonal patterns; wavelet-based speech analysis; wavelet-based speech signal feature extraction; Cochlear implants; Data mining; Feature extraction; Frequency; Natural languages; Signal generators; Signal processing; Speech analysis; Speech processing; Wavelet analysis;
Conference_Titel :
[Engineering in Medicine and Biology, 1999. 21st Annual Conference and the 1999 Annual Fall Meetring of the Biomedical Engineering Society] BMES/EMBS Conference, 1999. Proceedings of the First Joint
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-5674-8
DOI :
10.1109/IEMBS.1999.802732
