ZCU-NTIS Speaker Diarization System for the DIHARD 2018 Challenge

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F18%3A43952579" target="_blank" >RIV/49777513:23520/18:43952579 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.isca-speech.org/archive/Interspeech_2018/abstracts/1252.html" target="_blank" >https://www.isca-speech.org/archive/Interspeech_2018/abstracts/1252.html</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2018-1252" target="_blank" >10.21437/Interspeech.2018-1252</a>

Jazyk výsledku

angličtina

Název v původním jazyce

ZCU-NTIS Speaker Diarization System for the DIHARD 2018 Challenge

Popis výsledku v původním jazyce

In this paper, we present the system developed by the team from the New Technologies for the Information Society (NTIS) research center of the University of West Bohemia, for the First DIHARD Speech Diarization Challenge. The base of our system follows the currently-standard approach of segmentation, i-vector extraction, clustering, and resegmentation. Here, we describe the modifications to the system which allowed us to apply it to data from a range of different domains. The main contribution to our achievement is a Neural Network (NN) based domain classifier, which categorizes each conversation into one of the ten domains present in the development set. This classification determines the specific system configuration, such as the expected number of speakers and the stopping criterion for the hierarchical clustering. At the time of writing of this abstract, our best submission achieves a DER of 26.90% and an MI of 8.34 bits on the evaluation set (gold speech/nonspeech segmentation).

Název v anglickém jazyce

ZCU-NTIS Speaker Diarization System for the DIHARD 2018 Challenge

Popis výsledku anglicky

In this paper, we present the system developed by the team from the New Technologies for the Information Society (NTIS) research center of the University of West Bohemia, for the First DIHARD Speech Diarization Challenge. The base of our system follows the currently-standard approach of segmentation, i-vector extraction, clustering, and resegmentation. Here, we describe the modifications to the system which allowed us to apply it to data from a range of different domains. The main contribution to our achievement is a Neural Network (NN) based domain classifier, which categorizes each conversation into one of the ten domains present in the development set. This classification determines the specific system configuration, such as the expected number of speakers and the stopping criterion for the hierarchical clustering. At the time of writing of this abstract, our best submission achieves a DER of 26.90% and an MI of 8.34 bits on the evaluation set (gold speech/nonspeech segmentation).

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 19th Annual Conference of the International Speech Communication Association (Interspeech 2018)

ISBN

978-1-5108-7221-9

ISSN

2308-457X

e-ISSN

neuvedeno

Počet stran výsledku

5

Strana od-do

2788-2792

Název nakladatele

Curran Associates, Inc.

Místo vydání

Red Hook, NY

Místo konání akce

Hyderabad, Indie

Datum konání akce

2. 9. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—