26 April 2006 Speaker identification based on kernel Ho-Kashyap classifier
Author Affiliations +
Proceedings Volume 6159, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments IV; 61594A (2006) https://doi.org/10.1117/12.674961
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments IV, 2005, Wilga, Poland
Abstract
This paper presents application of kernel Ho-Kashyap KHK classifier to speaker identification. Since this classifier achieves very good performance for most benchmark data sets used in machine learning, it was very interesting to check its performance in speaker identification which is a slightly different problem. Comparison of achieved identification accuracy with popular modeling techniques in speaker recognition like Gaussian mixture models and vector quantization is made. All research is based on Polish speech corpus ROBOT, which is designed for testing speech algorithms. Identification results are discussed.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Adam Dustor, Adam Dustor, } "Speaker identification based on kernel Ho-Kashyap classifier", Proc. SPIE 6159, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments IV, 61594A (26 April 2006); doi: 10.1117/12.674961; https://doi.org/10.1117/12.674961
PROCEEDINGS
6 PAGES


SHARE
Back to Top