@inproceedings{kantarci-etal-2026-turksv,
title = "{T}urk{SV}-Bench: Assessing Demographic Bias and Preprocessing Effects in Speaker Verification",
author = "Kantarc{\i}, Ahmet Berkay and
Parlak, Abdulkadir and
Karazor, Ahmet",
editor = "Shekhar, Ravi and
Swain, Monorama and
Mishra, Jagabandhu and
Dhar, Sandipan and
Mouratidis, Haralambos and
Purver, Matthew",
booktitle = "Proceedings of the {IMPACT}-{SPEECH} Workshop: Identifying, Measuring, Preventing, and Assessing Consequences of Bias in Speech {LLM}s",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.impactspeech-1.9/",
pages = "95--103",
ISBN = "979-8-89176-479-8",
abstract = "In this study, TurkSV-Bench is introduced as a novel benchmark dataset to evaluate the zero-shot cross-lingual performance and demographic biases of Turkish speaker verification (SV) systems. Created via an automated pipeline from YouTube data, this dataset comprises 1,844 audio recordings from 461 speakers representing diverse age groups, genders, and regional dialects. Evaluation of existing models identifies ResNet34-LM as the most successful baseline architecture. Subgroup analyses demonstrate the models' generalization capabilities across different gender and age demographics, while revealing distinct performance variations among regional dialects. Comprehensive evaluations of various preprocessing techniques highlight the baseline architecture{'}s structural robustness, identifying specific configurations that maintain or refine verification performance without requiring aggressive signal filtering."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kantarci-etal-2026-turksv">
<titleInfo>
<title>TurkSV-Bench: Assessing Demographic Bias and Preprocessing Effects in Speaker Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmet</namePart>
<namePart type="given">Berkay</namePart>
<namePart type="family">Kantarcı</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulkadir</namePart>
<namePart type="family">Parlak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmet</namePart>
<namePart type="family">Karazor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the IMPACT-SPEECH Workshop: Identifying, Measuring, Preventing, and Assessing Consequences of Bias in Speech LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ravi</namePart>
<namePart type="family">Shekhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monorama</namePart>
<namePart type="family">Swain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jagabandhu</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandipan</namePart>
<namePart type="family">Dhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haralambos</namePart>
<namePart type="family">Mouratidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-479-8</identifier>
</relatedItem>
<abstract>In this study, TurkSV-Bench is introduced as a novel benchmark dataset to evaluate the zero-shot cross-lingual performance and demographic biases of Turkish speaker verification (SV) systems. Created via an automated pipeline from YouTube data, this dataset comprises 1,844 audio recordings from 461 speakers representing diverse age groups, genders, and regional dialects. Evaluation of existing models identifies ResNet34-LM as the most successful baseline architecture. Subgroup analyses demonstrate the models’ generalization capabilities across different gender and age demographics, while revealing distinct performance variations among regional dialects. Comprehensive evaluations of various preprocessing techniques highlight the baseline architecture’s structural robustness, identifying specific configurations that maintain or refine verification performance without requiring aggressive signal filtering.</abstract>
<identifier type="citekey">kantarci-etal-2026-turksv</identifier>
<location>
<url>https://aclanthology.org/2026.impactspeech-1.9/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>95</start>
<end>103</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TurkSV-Bench: Assessing Demographic Bias and Preprocessing Effects in Speaker Verification
%A Kantarcı, Ahmet Berkay
%A Parlak, Abdulkadir
%A Karazor, Ahmet
%Y Shekhar, Ravi
%Y Swain, Monorama
%Y Mishra, Jagabandhu
%Y Dhar, Sandipan
%Y Mouratidis, Haralambos
%Y Purver, Matthew
%S Proceedings of the IMPACT-SPEECH Workshop: Identifying, Measuring, Preventing, and Assessing Consequences of Bias in Speech LLMs
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-479-8
%F kantarci-etal-2026-turksv
%X In this study, TurkSV-Bench is introduced as a novel benchmark dataset to evaluate the zero-shot cross-lingual performance and demographic biases of Turkish speaker verification (SV) systems. Created via an automated pipeline from YouTube data, this dataset comprises 1,844 audio recordings from 461 speakers representing diverse age groups, genders, and regional dialects. Evaluation of existing models identifies ResNet34-LM as the most successful baseline architecture. Subgroup analyses demonstrate the models’ generalization capabilities across different gender and age demographics, while revealing distinct performance variations among regional dialects. Comprehensive evaluations of various preprocessing techniques highlight the baseline architecture’s structural robustness, identifying specific configurations that maintain or refine verification performance without requiring aggressive signal filtering.
%U https://aclanthology.org/2026.impactspeech-1.9/
%P 95-103
Markdown (Informal)
[TurkSV-Bench: Assessing Demographic Bias and Preprocessing Effects in Speaker Verification](https://aclanthology.org/2026.impactspeech-1.9/) (Kantarcı et al., IMPACT-SPEECH 2026)
ACL