Speaker identification using vector quantization

Kód výsledku v 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>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Speaker identification using vector quantization

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Speaker identification using vector quantization

Popis výsledku anglicky

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.

Druh

C - Kapitola v odborné knize

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/GV102%2F96%2FK087" target="_blank" >GV102/96/K087: Teorie a aplikace hlasové komunikace v Češtině</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

1999

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název knihy nebo sborníku

Speaker identification using vector quantization

ISBN

8070833394

Počet stran výsledku

4

Strana od-do

—

Počet stran knihy

—

Název nakladatele

Technická univerzita

Místo vydání

Liberec

Kód UT WoS kapitoly

—