Title :
Comparison of clustering methods for MLP-based speaker verification
Author :
Um, Ig-Tae ; Ra, Jong-Hei ; Kim, Moon-Hyun
Author_Institution :
Sungkyunkwan Univ., Kyunggi, South Korea
Abstract :
This paper compares two clustering methods: SOM, and a graph-based clustering technique , for text-independent speaker verification. The focus of comparison is given to the distribution characteristics of representative frames for each cluster, to the use of processing time of clustering and MLP learning, and to verification performance. Simulation results show that the graph-based technique produces better verification performance than SOM. Other statistics are collected to explain significant difference in MLP learning time with each clustering method. This experiment suggests that there is a best match between a classifier and a clustering method for a given application
Keywords :
computational complexity; graph theory; multilayer perceptrons; pattern clustering; speaker recognition; MLP learning time; MLP-based speaker verification; SOM; classifier; distribution characteristics; graph-based clustering technique; processing time; representative frames; text-independent speaker verification; verification performance; Cepstral analysis; Clustering algorithms; Clustering methods; Hidden Markov models; Mel frequency cepstral coefficient; Neural networks; Speech; Statistical distributions; Testing; Training data;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.906115