Text-Independent Speaker Identification by Genetic Clustering Radial Basis Function Neural Network
Abstract
The authors combine genetic clustering algorithm with radial basis function neural network (RBFNN) for avoiding locally optimum solutions in speaker identification. The effectiveness of genetic clustering algorithm is evaluated with speech utterances by comparing with normal clustering method. Speaker identification experiments show that generic clustering RBFNN can improve the correctness of text-independent speaker identification.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 25, 2001
- Accession Number
- ADA412429
Entities
People
- Datian Ye
- Ming Liu
- Xicai Yue
Organizations
- Tsinghua University