@inproceedings{simonotti-etal-2026-semi,
title = "Is Semi-Automatic Transcription Useful in Corpus Creation? Preliminary Considerations on the {KIP}arla Corpus",
author = "Simonotti, Martina and
Pannitto, Ludovica and
Zucchini, Eleonora and
Ballar{\`e}, Silvia and
Mauri, Caterina",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.520/",
doi = "10.63317/3gw6i7cbs5rc",
pages = "6547--6560",
abstract = "This paper analyses the implementation of Automatic Speech Recognition (ASR) into the transcription workflow of the KIParla corpus, a resource of spoken Italian. Through a two-phase experiment, 11 expert and novice transcribers produced both manual and ASR-assisted transcriptions of identical audio segments across three different types of conversation, which were subsequently analyzed through a combination of statistical modeling, word-level alignment and a series of annotation-based metrics. Results show that ASR-assisted workflows can increase transcription speed but do not systemically improve accuracy or prosodic annotation quality. Improvements appear to depend on multiple factors, including workflow configuration, conversation type and annotator experience. These findings are therefore yet not generalizable and highlight the complex interplay between transcription expertise, data type and workflow design. Despite current limitations, ASR-assisted transcription, potentially when supported by task-specific fine-tuning, could be integrated into the KIParla transcription workflow to accelerate corpus creation without compromising linguistic and annotation quality. More broadly, this work underscores the potential of semi-automatic transcription for corpus building, especially in complex settings involving multiple speakers and spontaneous, conversational data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simonotti-etal-2026-semi">
<titleInfo>
<title>Is Semi-Automatic Transcription Useful in Corpus Creation? Preliminary Considerations 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">Eleonora</namePart>
<namePart type="family">Zucchini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvia</namePart>
<namePart type="family">Ballarè</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>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper analyses the implementation of Automatic Speech Recognition (ASR) into the transcription workflow of the KIParla corpus, a resource of spoken Italian. Through a two-phase experiment, 11 expert and novice transcribers produced both manual and ASR-assisted transcriptions of identical audio segments across three different types of conversation, which were subsequently analyzed through a combination of statistical modeling, word-level alignment and a series of annotation-based metrics. Results show that ASR-assisted workflows can increase transcription speed but do not systemically improve accuracy or prosodic annotation quality. Improvements appear to depend on multiple factors, including workflow configuration, conversation type and annotator experience. These findings are therefore yet not generalizable and highlight the complex interplay between transcription expertise, data type and workflow design. Despite current limitations, ASR-assisted transcription, potentially when supported by task-specific fine-tuning, could be integrated into the KIParla transcription workflow to accelerate corpus creation without compromising linguistic and annotation quality. More broadly, this work underscores the potential of semi-automatic transcription for corpus building, especially in complex settings involving multiple speakers and spontaneous, conversational data.</abstract>
<identifier type="citekey">simonotti-etal-2026-semi</identifier>
<identifier type="doi">10.63317/3gw6i7cbs5rc</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.520/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>6547</start>
<end>6560</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Is Semi-Automatic Transcription Useful in Corpus Creation? Preliminary Considerations on the KIParla Corpus
%A Simonotti, Martina
%A Pannitto, Ludovica
%A Zucchini, Eleonora
%A Ballarè, Silvia
%A Mauri, Caterina
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F simonotti-etal-2026-semi
%X This paper analyses the implementation of Automatic Speech Recognition (ASR) into the transcription workflow of the KIParla corpus, a resource of spoken Italian. Through a two-phase experiment, 11 expert and novice transcribers produced both manual and ASR-assisted transcriptions of identical audio segments across three different types of conversation, which were subsequently analyzed through a combination of statistical modeling, word-level alignment and a series of annotation-based metrics. Results show that ASR-assisted workflows can increase transcription speed but do not systemically improve accuracy or prosodic annotation quality. Improvements appear to depend on multiple factors, including workflow configuration, conversation type and annotator experience. These findings are therefore yet not generalizable and highlight the complex interplay between transcription expertise, data type and workflow design. Despite current limitations, ASR-assisted transcription, potentially when supported by task-specific fine-tuning, could be integrated into the KIParla transcription workflow to accelerate corpus creation without compromising linguistic and annotation quality. More broadly, this work underscores the potential of semi-automatic transcription for corpus building, especially in complex settings involving multiple speakers and spontaneous, conversational data.
%R 10.63317/3gw6i7cbs5rc
%U https://aclanthology.org/2026.lrec-1.520/
%U https://doi.org/10.63317/3gw6i7cbs5rc
%P 6547-6560
Markdown (Informal)
[Is Semi-Automatic Transcription Useful in Corpus Creation? Preliminary Considerations on the KIParla Corpus](https://aclanthology.org/2026.lrec-1.520/) (Simonotti et al., LREC 2026)
ACL