Ideas for Clustering of Similar Models of a Speaker in an Online Speaker Diarization System

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F15%3A43926112" target="_blank" >RIV/49777513:23520/15:43926112 - isvavai.cz</a>

Výsledek na webu

<a href="http://link.springer.com/chapter/10.1007%2F978-3-319-24033-6_26" target="_blank" >http://link.springer.com/chapter/10.1007%2F978-3-319-24033-6_26</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-24033-6_26" target="_blank" >10.1007/978-3-319-24033-6_26</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Ideas for Clustering of Similar Models of a Speaker in an Online Speaker Diarization System

Popis výsledku v původním jazyce

During online speaker diarization, a situation may occur where a single speaker is being represented by several different models. Such situation leads to worsened diarization results, because the diarization system considers every change of a model to be a change of speakers. In the article we describe a method for detecting this situation and propose several ways of solving it. Experiments show that the most suitable option is treating multiple GMMs as belonging to a single speaker, i.e. updating all of them with the same data every time one of them is assigned a new segment. In that case, there was a relative improvement in Diarization Error Rate of 30.69% in comparison with the baseline system.

Název v anglickém jazyce

Ideas for Clustering of Similar Models of a Speaker in an Online Speaker Diarization System

Popis výsledku anglicky

During online speaker diarization, a situation may occur where a single speaker is being represented by several different models. Such situation leads to worsened diarization results, because the diarization system considers every change of a model to be a change of speakers. In the article we describe a method for detecting this situation and propose several ways of solving it. Experiments show that the most suitable option is treating multiple GMMs as belonging to a single speaker, i.e. updating all of them with the same data every time one of them is assigned a new segment. In that case, there was a relative improvement in Diarization Error Rate of 30.69% in comparison with the baseline system.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/GBP103%2F12%2FG084" target="_blank" >GBP103/12/G084: Centrum pro multi-modální interpretaci dat velkého rozsahu</a><br>

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název statě ve sborníku

Text, Speech, and Dialogue, 18th International Conference, TSD 2015, Pilsen, Czech Republic, 14-17, 2015. Proceedings

ISBN

978-3-319-24032-9

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

9

Strana od-do

225-233

Název nakladatele

Springer

Místo vydání

Berlin

Místo konání akce

Pilsen, Czech Republic

Datum konání akce

14. 9. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000365947800026