Speaker identification using vector quantization

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F99%3A00041859" target="_blank" >RIV/49777513:23520/99:00041859 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Speaker identification using vector quantization
Original language description
In this paper an approach to text independent speaker identification based on discrete vector quantization is presented. The identification experiments were performed in a closed group of 300 speakers. Three different experiments are described, in the discrete vector quantization in the combination with various signal processing methods were used. Three various types of features were tested - LPC coefficients, LPC cepstral coefficients and mel-frequency cepstral coefficients. The goal of these experiments was the compare the effect of various features upon the quality of identification. In all experiments over 97% of speakers were identified correctly. If we take into account the size of tested database, we can regard the identification results as verygood.
Czech name
—
Czech description
—

Project
<a href="/en/project/GV102%2F96%2FK087" target="_blank" >GV102/96/K087: Theory and application of speach communication in czech</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year
1999
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)