Title :
Speaker identification using singular value decomposition of LPC spectral magnitudes
Author :
Gopalan, K. ; Mahil, S.S.
Author_Institution :
Dept. of Eng., Purdue Univ. Calumet, Hammond, IN, USA
Abstract :
An experimental procedure for identification of speakers using singular value decomposition of spectral magnitudes of speech is described. Amplitude spectra at 10 discrete frequencies from 500 Hz to 5000 Hz, which are derived from a tenth order short-time linear predictive coding (LPC) model, are used as pattern vectors characterising speech utterances. The set of stored reference spectra yielding the largest ratio of singular values with the spectra of an unknown utterance is considered closest to the unknown. An overall identification score of 70% to 87.5%, depending on the frequency used, was observed on a set of 40 test utterances
Keywords :
linear predictive coding; speech coding; speech recognition; 500 to 5000 Hz; LPC spectral magnitudes; amplitude spectra; overall identification score; pattern vectors; singular value decomposition; speaker identification; speech utterances; stored reference spectra; tenth order short-time linear predictive coding; Eigenvalues and eigenfunctions; Filters; Frequency; Linear predictive coding; Matrix decomposition; Predictive models; Singular value decomposition; Speaker recognition; Speech analysis; Testing;
Conference_Titel :
Circuits and Systems, 1992., Proceedings of the 35th Midwest Symposium on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-0510-8
DOI :
10.1109/MWSCAS.1992.271138
