Title :
A modular connectionist architecture for text-independent talker identification
Author :
Bennani, Younes ; Gallinari, Patrick
Author_Institution :
Lab. de Recherche en Inf., Univ. de Paris-Sud, Orsay, France
Abstract :
The authors propose a novel model for text-independent talker identification which uses TDNN (time-delay neural network)-extracted features information. This model has been tested on 20 speakers, ten male and ten female, from the TIMIT database using an LPC (linear prediction coding) parameterization. An average identification of 98% has been observed
Keywords :
delays; encoding; neural nets; speech recognition; TIMIT database; linear prediction coding; modular connectionist architecture; parameterization; text-independent talker identification; time-delay neural network; Data mining; Decision making; Feature extraction; Linear predictive coding; Logic; Neural networks; Spatial databases; Speech recognition; TV; Testing;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155446
