Skip to main navigation Skip to search Skip to main content

Biometric Voice Identification Based on Fuzzy Kernel Classifier

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

15 Citations (Scopus)

Abstract

This paper presents research on automatic speaker identification based on structural risk minimization and kernel functions. New approach, known as a Fuzzy Kernel Ho-Kashyap classifier FKHK, to speaker identification was applied. Instead of the most popular kernel functions like gaussian or polynomial, data dependent kernel matrix which may be interpreted in terms of linguistic values from the premises of if-then rules was applied. Classifier was tested on polish speech corpora ROBOT and obtained results were discussed.

Original languageEnglish
Title of host publicationComputer Networks - 20th International Conference, CN 2013, Proceedings
PublisherSpringer Verlag
Pages456-465
Number of pages10
ISBN (Print)9783642388644
DOIs
Publication statusPublished - 2013
Event20th International Science Conference Computer Networks, CN 2013 - Lwowek Slaski, Poland
Duration: 17 Jun 201321 Jun 2013

Publication series

NameCommunications in Computer and Information Science
Volume370 CCIS
ISSN (Print)1865-0929

Conference

Conference20th International Science Conference Computer Networks, CN 2013
Country/TerritoryPoland
CityLwowek Slaski
Period17/06/1321/06/13

Keywords

  • biometrics
  • security
  • speaker identification
  • voice identification

ASJC Scopus subject areas

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'Biometric Voice Identification Based on Fuzzy Kernel Classifier'. Together they form a unique fingerprint.

Cite this