@inproceedings{cacioli-2026-whisper,
title = "When Whisper Italianizes: Measuring and Mitigating Dialect Substitution Bias in {N}eapolitan {ASR}",
author = "Cacioli, Michael",
editor = "Adelani, David Ifeoluwa and
Alabi, Jesujoba and
Arnett, Catherine and
Chang, Tyler and
Downey, C.M. and
Goldman, Omer and
Li, Senyu and
Miranda, Lester James Validad and
Qi, Jirui and
Stap, David and
Winata, Genta Indra and
Zhang, Xinyu Crystina",
booktitle = "Proceedings of the 6th Workshop on Multilingual Representation Learning ({MRL} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mrl-1.42/",
pages = "519--532",
ISBN = "979-8-89176-469-9",
abstract = "Multilingual ASR foundation models trained on high-resource standard languages possess a failure mode invisible to WER: transcribing closely related low-resource varieties leads to systematic substitution of dialect-marked content with standard-language counterparts. We investigate this phenomenon, termed Italianization, using Whisper on Neapolitan, a low-resource variety of Italian. We introduce Italianization Error Rate (IER), based on a 115-item native-speaker-validated lexicon and complemented by a lexicon-free GlotLID-ratio signal. Using an expanded Neapolitan Spoken Corpus (591 clips, 3 domains, 4 speakers), we observe three phenomena: 1) zero-shot Whisper from small to medium improves WER (81.24{\%} to 78.53{\%}), yet worsens IER by 44.5{\%} relative (0.1375 to 0.1987). Capacity increases, as does the bias; 2) LoRA-finetuning, under leave-one-speaker-out training and evaluation, reduces IER by 54.9{\%} to 69.2{\%} relative to the zero-shot system. This entirely undoes the capacity penalty, as adapted Whisper-medium performs on par with adapted Whisper-small on IER and maintains a 6.51 pp advantage in WER; 3) manual error analysis over 120 stratified clips demonstrates that, although phonetic hallucination is the dominant error mode at the clip level, Italianization is reduced by adaptation. LoRA{'}s largest qualitative effect is a near-complete elimination of non-recognition errors (from 10{\%} to 2{\%}). We release our corpus, lexicon, splits, LoRA adapters, and annotation data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cacioli-2026-whisper">
<titleInfo>
<title>When Whisper Italianizes: Measuring and Mitigating Dialect Substitution Bias in Neapolitan ASR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Cacioli</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 6th Workshop on Multilingual Representation Learning (MRL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="given">Validad</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jirui</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</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">979-8-89176-469-9</identifier>
</relatedItem>
<abstract>Multilingual ASR foundation models trained on high-resource standard languages possess a failure mode invisible to WER: transcribing closely related low-resource varieties leads to systematic substitution of dialect-marked content with standard-language counterparts. We investigate this phenomenon, termed Italianization, using Whisper on Neapolitan, a low-resource variety of Italian. We introduce Italianization Error Rate (IER), based on a 115-item native-speaker-validated lexicon and complemented by a lexicon-free GlotLID-ratio signal. Using an expanded Neapolitan Spoken Corpus (591 clips, 3 domains, 4 speakers), we observe three phenomena: 1) zero-shot Whisper from small to medium improves WER (81.24% to 78.53%), yet worsens IER by 44.5% relative (0.1375 to 0.1987). Capacity increases, as does the bias; 2) LoRA-finetuning, under leave-one-speaker-out training and evaluation, reduces IER by 54.9% to 69.2% relative to the zero-shot system. This entirely undoes the capacity penalty, as adapted Whisper-medium performs on par with adapted Whisper-small on IER and maintains a 6.51 pp advantage in WER; 3) manual error analysis over 120 stratified clips demonstrates that, although phonetic hallucination is the dominant error mode at the clip level, Italianization is reduced by adaptation. LoRA’s largest qualitative effect is a near-complete elimination of non-recognition errors (from 10% to 2%). We release our corpus, lexicon, splits, LoRA adapters, and annotation data.</abstract>
<identifier type="citekey">cacioli-2026-whisper</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.42/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>519</start>
<end>532</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Whisper Italianizes: Measuring and Mitigating Dialect Substitution Bias in Neapolitan ASR
%A Cacioli, Michael
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F cacioli-2026-whisper
%X Multilingual ASR foundation models trained on high-resource standard languages possess a failure mode invisible to WER: transcribing closely related low-resource varieties leads to systematic substitution of dialect-marked content with standard-language counterparts. We investigate this phenomenon, termed Italianization, using Whisper on Neapolitan, a low-resource variety of Italian. We introduce Italianization Error Rate (IER), based on a 115-item native-speaker-validated lexicon and complemented by a lexicon-free GlotLID-ratio signal. Using an expanded Neapolitan Spoken Corpus (591 clips, 3 domains, 4 speakers), we observe three phenomena: 1) zero-shot Whisper from small to medium improves WER (81.24% to 78.53%), yet worsens IER by 44.5% relative (0.1375 to 0.1987). Capacity increases, as does the bias; 2) LoRA-finetuning, under leave-one-speaker-out training and evaluation, reduces IER by 54.9% to 69.2% relative to the zero-shot system. This entirely undoes the capacity penalty, as adapted Whisper-medium performs on par with adapted Whisper-small on IER and maintains a 6.51 pp advantage in WER; 3) manual error analysis over 120 stratified clips demonstrates that, although phonetic hallucination is the dominant error mode at the clip level, Italianization is reduced by adaptation. LoRA’s largest qualitative effect is a near-complete elimination of non-recognition errors (from 10% to 2%). We release our corpus, lexicon, splits, LoRA adapters, and annotation data.
%U https://aclanthology.org/2026.mrl-1.42/
%P 519-532
Markdown (Informal)
[When Whisper Italianizes: Measuring and Mitigating Dialect Substitution Bias in Neapolitan ASR](https://aclanthology.org/2026.mrl-1.42/) (Cacioli, MRL 2026)
ACL