@inproceedings{simonotti-etal-2026-say,
title = "Say Again? The Limits of Whisper with Conversation. A Case Study on the {KIP}arla Corpus.",
author = "Simonotti, Martina and
Pannitto, Ludovica and
Mauri, Caterina and
Ferraresi, Adriano and
Carioli, Gabriele",
editor = "Hosseini-Kivanani, Nina and
Brutti, Alessio and
Matassoni, Marco and
Dowerah, Sandipana and
Liga, Davide and
Schommer, Christoph",
booktitle = "Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis ({SPEAKABLE}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.speakable-1.3/",
doi = "10.63317/2so5y449gb4w",
pages = "16--30",
abstract = "This study investigates how Whisper handles interactional phenomena in spontaneous Italian conversation, focusing on backchannels, repairs, and filled pauses. We compare standard Word Error Rate (WER) optimization with a decoding strategy that explicitly rewards the preservation of interactional events. Results show that decoding choices have limited impact on overall accuracy, while recognition remains strongly phenomenon-dependent, suggesting structural limitations in the handling of interactional phenomena, with systematic linearization of repairs and frequent suppression of short conversational items."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simonotti-etal-2026-say">
<titleInfo>
<title>Say Again? The Limits of Whisper with Conversation. A Case Study on the KIParla Corpus.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martina</namePart>
<namePart type="family">Simonotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ludovica</namePart>
<namePart type="family">Pannitto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caterina</namePart>
<namePart type="family">Mauri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adriano</namePart>
<namePart type="family">Ferraresi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Carioli</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 Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Hosseini-Kivanani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessio</namePart>
<namePart type="family">Brutti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Matassoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandipana</namePart>
<namePart type="family">Dowerah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Liga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Schommer</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 study investigates how Whisper handles interactional phenomena in spontaneous Italian conversation, focusing on backchannels, repairs, and filled pauses. We compare standard Word Error Rate (WER) optimization with a decoding strategy that explicitly rewards the preservation of interactional events. Results show that decoding choices have limited impact on overall accuracy, while recognition remains strongly phenomenon-dependent, suggesting structural limitations in the handling of interactional phenomena, with systematic linearization of repairs and frequent suppression of short conversational items.</abstract>
<identifier type="citekey">simonotti-etal-2026-say</identifier>
<identifier type="doi">10.63317/2so5y449gb4w</identifier>
<location>
<url>https://aclanthology.org/2026.speakable-1.3/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>16</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Say Again? The Limits of Whisper with Conversation. A Case Study on the KIParla Corpus.
%A Simonotti, Martina
%A Pannitto, Ludovica
%A Mauri, Caterina
%A Ferraresi, Adriano
%A Carioli, Gabriele
%Y Hosseini-Kivanani, Nina
%Y Brutti, Alessio
%Y Matassoni, Marco
%Y Dowerah, Sandipana
%Y Liga, Davide
%Y Schommer, Christoph
%S Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F simonotti-etal-2026-say
%X This study investigates how Whisper handles interactional phenomena in spontaneous Italian conversation, focusing on backchannels, repairs, and filled pauses. We compare standard Word Error Rate (WER) optimization with a decoding strategy that explicitly rewards the preservation of interactional events. Results show that decoding choices have limited impact on overall accuracy, while recognition remains strongly phenomenon-dependent, suggesting structural limitations in the handling of interactional phenomena, with systematic linearization of repairs and frequent suppression of short conversational items.
%R 10.63317/2so5y449gb4w
%U https://aclanthology.org/2026.speakable-1.3/
%U https://doi.org/10.63317/2so5y449gb4w
%P 16-30
Markdown (Informal)
[Say Again? The Limits of Whisper with Conversation. A Case Study on the KIParla Corpus.](https://aclanthology.org/2026.speakable-1.3/) (Simonotti et al., SPEAKABLE 2026)
ACL