@inproceedings{fischbach-2024-comparative,
title = "A Comparative Analysis of Speaker Diarization Models: Creating a Dataset for {G}erman Dialectal Speech",
author = "Fischbach, Lea",
editor = "Serikov, Oleg and
Voloshina, Ekaterina and
Postnikova, Anna and
Muradoglu, Saliha and
Le Ferrand, Eric and
Klyachko, Elena and
Vylomova, Ekaterina and
Shavrina, Tatiana and
Tyers, Francis",
booktitle = "Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.fieldmatters-1.6",
pages = "43--51",
abstract = "Speaker diarization is a critical task in the field of computer science, aiming to assign timestamps and speaker labels to audio segments. The aim of these tests in this Publication is to find a pretrained speaker diarization pipeline capable of distinguishing dialectal speakers from each other and an explorer. To achieve this, three pipelines, namely Pyannote, CLEAVER and NeMo, are tested and compared, across various segmentation and parameterization strategies. The study considers multiple scenarios, such as the impact of threshold values, overlap handling, and minimum duration parameters, on classification accuracy. Additionally, this study aims to create a dataset for German dialect identification (DID) based on the findings from this research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fischbach-2024-comparative">
<titleInfo>
<title>A Comparative Analysis of Speaker Diarization Models: Creating a Dataset for German Dialectal Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lea</namePart>
<namePart type="family">Fischbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Serikov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Voloshina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Postnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="family">Muradoglu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Le Ferrand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Klyachko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Shavrina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Speaker diarization is a critical task in the field of computer science, aiming to assign timestamps and speaker labels to audio segments. The aim of these tests in this Publication is to find a pretrained speaker diarization pipeline capable of distinguishing dialectal speakers from each other and an explorer. To achieve this, three pipelines, namely Pyannote, CLEAVER and NeMo, are tested and compared, across various segmentation and parameterization strategies. The study considers multiple scenarios, such as the impact of threshold values, overlap handling, and minimum duration parameters, on classification accuracy. Additionally, this study aims to create a dataset for German dialect identification (DID) based on the findings from this research.</abstract>
<identifier type="citekey">fischbach-2024-comparative</identifier>
<location>
<url>https://aclanthology.org/2024.fieldmatters-1.6</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>43</start>
<end>51</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comparative Analysis of Speaker Diarization Models: Creating a Dataset for German Dialectal Speech
%A Fischbach, Lea
%Y Serikov, Oleg
%Y Voloshina, Ekaterina
%Y Postnikova, Anna
%Y Muradoglu, Saliha
%Y Le Ferrand, Eric
%Y Klyachko, Elena
%Y Vylomova, Ekaterina
%Y Shavrina, Tatiana
%Y Tyers, Francis
%S Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F fischbach-2024-comparative
%X Speaker diarization is a critical task in the field of computer science, aiming to assign timestamps and speaker labels to audio segments. The aim of these tests in this Publication is to find a pretrained speaker diarization pipeline capable of distinguishing dialectal speakers from each other and an explorer. To achieve this, three pipelines, namely Pyannote, CLEAVER and NeMo, are tested and compared, across various segmentation and parameterization strategies. The study considers multiple scenarios, such as the impact of threshold values, overlap handling, and minimum duration parameters, on classification accuracy. Additionally, this study aims to create a dataset for German dialect identification (DID) based on the findings from this research.
%U https://aclanthology.org/2024.fieldmatters-1.6
%P 43-51
Markdown (Informal)
[A Comparative Analysis of Speaker Diarization Models: Creating a Dataset for German Dialectal Speech](https://aclanthology.org/2024.fieldmatters-1.6) (Fischbach, FieldMatters-WS 2024)
ACL