@inproceedings{namdarzadeh-ballier-2026-fine,
title = "Fine-tuning Whisper with Spontaneous {P}ersian Speech ({SPS})",
author = "Namdarzadeh, Behnoosh and
Ballier, Nicolas",
editor = "Ojha, Atul Kr. and
Sakti, Sakriani and
Soria, Claudia and
Melero, Maite and
McCrae, John P. and
Lignos, Constantine and
Liu, Chao-Hong and
Claramunt, German Rigau and
Rehm, Georg",
booktitle = "Proceedings of the {SIGUL} 2026 Joint Workshop with {ELE}, {EURALI}, and {DCLRL}: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages",
month = may,
year = "2026",
address = "Palma, Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.sigul-1.26/",
doi = "10.63317/2ca2yoj8fzgd",
pages = "263--269",
abstract = "This paper introduces the Spontaneous Persian Speech (SPS) dataset designed for automatic speech recognition (ASR) tasks and a methodology laying the groundwork for addressing the shortage of spontaneous speech data. The corpus aims to support research on natural and conversational Persian, which remains under-represented in current ASR resources. The dataset consists of 694 minutes of audio from a total of 65 speakers, including 34 male and 31 female speakers. It contains 526,585 tokens. The audio segmentation step produces intervals of 1.24 to 3.25 seconds, each containing 3 to 9 words. The recordings cover a variety of environments, from inside cars to homes and shopping areas, including both busy and quiet settings. We use the SPS dataset to fine-tune Whisper and the performance increases significantly for both the small and medium models based on Word Error Rate (WER). This could be an initiative toward building domain-oriented datasets for specific ASR tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="namdarzadeh-ballier-2026-fine">
<titleInfo>
<title>Fine-tuning Whisper with Spontaneous Persian Speech (SPS)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Behnoosh</namePart>
<namePart type="family">Namdarzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Ballier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="given">Rigau</namePart>
<namePart type="family">Claramunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces the Spontaneous Persian Speech (SPS) dataset designed for automatic speech recognition (ASR) tasks and a methodology laying the groundwork for addressing the shortage of spontaneous speech data. The corpus aims to support research on natural and conversational Persian, which remains under-represented in current ASR resources. The dataset consists of 694 minutes of audio from a total of 65 speakers, including 34 male and 31 female speakers. It contains 526,585 tokens. The audio segmentation step produces intervals of 1.24 to 3.25 seconds, each containing 3 to 9 words. The recordings cover a variety of environments, from inside cars to homes and shopping areas, including both busy and quiet settings. We use the SPS dataset to fine-tune Whisper and the performance increases significantly for both the small and medium models based on Word Error Rate (WER). This could be an initiative toward building domain-oriented datasets for specific ASR tasks.</abstract>
<identifier type="citekey">namdarzadeh-ballier-2026-fine</identifier>
<identifier type="doi">10.63317/2ca2yoj8fzgd</identifier>
<location>
<url>https://aclanthology.org/2026.sigul-1.26/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>263</start>
<end>269</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-tuning Whisper with Spontaneous Persian Speech (SPS)
%A Namdarzadeh, Behnoosh
%A Ballier, Nicolas
%Y Ojha, Atul Kr.
%Y Sakti, Sakriani
%Y Soria, Claudia
%Y Melero, Maite
%Y McCrae, John P.
%Y Lignos, Constantine
%Y Liu, Chao-Hong
%Y Claramunt, German Rigau
%Y Rehm, Georg
%S Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F namdarzadeh-ballier-2026-fine
%X This paper introduces the Spontaneous Persian Speech (SPS) dataset designed for automatic speech recognition (ASR) tasks and a methodology laying the groundwork for addressing the shortage of spontaneous speech data. The corpus aims to support research on natural and conversational Persian, which remains under-represented in current ASR resources. The dataset consists of 694 minutes of audio from a total of 65 speakers, including 34 male and 31 female speakers. It contains 526,585 tokens. The audio segmentation step produces intervals of 1.24 to 3.25 seconds, each containing 3 to 9 words. The recordings cover a variety of environments, from inside cars to homes and shopping areas, including both busy and quiet settings. We use the SPS dataset to fine-tune Whisper and the performance increases significantly for both the small and medium models based on Word Error Rate (WER). This could be an initiative toward building domain-oriented datasets for specific ASR tasks.
%R 10.63317/2ca2yoj8fzgd
%U https://aclanthology.org/2026.sigul-1.26/
%U https://doi.org/10.63317/2ca2yoj8fzgd
%P 263-269
Markdown (Informal)
[Fine-tuning Whisper with Spontaneous Persian Speech (SPS)](https://aclanthology.org/2026.sigul-1.26/) (Namdarzadeh & Ballier, SIGUL-EURALI-DCLRL 2026)
ACL
- Behnoosh Namdarzadeh and Nicolas Ballier. 2026. Fine-tuning Whisper with Spontaneous Persian Speech (SPS). In Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages, pages 263–269, Palma, Mallorca, Spain. ELRA Language Resources Association (ELRA).