Speaker verification as a target-nontarget trial task

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F09%3APU82682" target="_blank" >RIV/00216305:26230/09:PU82682 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Speaker verification as a target-nontarget trial task

Popis výsledku v původním jazyce

This paper deals with a speaker detection task. In this work, a different interpretation of the problem is introduced than the one used so far. In the standard approach, each speaker is modeled by their own model and the task is to decide whether the test speech segment was generated by the given model or not. In this work, only two models are used: one represents the target trials and the other represents nontarget trials, where the trial is represented by two speech segments, both from the same speaker, and two from different speakers, respectively. As the input features, fixed-length low-dimensional vectors derived from speaker factors generated by Joint Factor Analysis are used. Gaussian Mixture Models framework is used to model the feature distribution. The achieved results are compared to the state of the art systems.

Název v anglickém jazyce

Speaker verification as a target-nontarget trial task

Popis výsledku anglicky

This paper deals with a speaker detection task. In this work, a different interpretation of the problem is introduced than the one used so far. In the standard approach, each speaker is modeled by their own model and the task is to decide whether the test speech segment was generated by the given model or not. In this work, only two models are used: one represents the target trials and the other represents nontarget trials, where the trial is represented by two speech segments, both from the same speaker, and two from different speakers, respectively. As the input features, fixed-length low-dimensional vectors derived from speaker factors generated by Joint Factor Analysis are used. Gaussian Mixture Models framework is used to model the feature distribution. The achieved results are compared to the state of the art systems.

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

<a href="/cs/project/7E08042" target="_blank" >7E08042: Mobile Biometry</a><br>

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2009

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 15th Conference and Competition STUDENT EEICT 2009

ISBN

978-80-214-3870-5

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

—

Název nakladatele

Faculty of Electrical Engineering and Communication BUT

Místo vydání

Brno

Místo konání akce

FEKT VUT v Brně

Datum konání akce

23. 4. 2009

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

—