@inproceedings{szalay-etal-2026-auskidtalk,
title = "{A}us{K}id{T}alk: Developing Transcription Guidelines for Continuous {A}ustralian {E}nglish Child Speech",
author = "Szalay, Tuende and
Nan, Zheng and
Huang, Renata and
Shahin, Mostafa and
Tharmakulasingam, Sirojan and
Ballard, Kirrie and
Ahmed, Beena",
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-1.458/",
doi = "10.63317/4j6otnjq8c3n",
pages = "5794--5804",
abstract = "Guidelines are required for accurate and consistent transcription of speech corpora, especially when they contain more challenging, e.g. spontaneous or under-resourced speech. This paper presents a workflow and guidelines for transcribing spontaneous and under-resourced child speech in AusKidTalk, the first Australian English child corpus. Speech samples were elicited using a story-telling task and are 3.5 minutes long per child on average. Orthographic transcriptions were generated using automatic speech recognition (ASR) tools and corrected manually. A novel hand-correction protocol consisting of guidelines, hand-correction interface, and ground truth transcriptions together with consistency metrics were developed. Nine annotators submitted hand-corrections for 261 children{'}s story-telling task, and 25 ground truth tasks. Manual correction was 11-fold of speech time with a 3.5-minute-long story-telling task corrected in approximately 40 minutes. Efficiency is attributed to the quality of automatic transcription with 23{\%} word error rate. Manual correction was accurate with annotators achieving consistent results on 15/25 ground truth submissions. Most inconsistent ground truth submissions were caused by a single, challenging ground truth task. These results show that our workflow yields efficient and accurate transcriptions, although transcriptions of potentially more challenging narrative tasks (e.g., elicited from younger children) might require further corrections."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="szalay-etal-2026-auskidtalk">
<titleInfo>
<title>AusKidTalk: Developing Transcription Guidelines for Continuous Australian English Child Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tuende</namePart>
<namePart type="family">Szalay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Nan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renata</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mostafa</namePart>
<namePart type="family">Shahin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirojan</namePart>
<namePart type="family">Tharmakulasingam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirrie</namePart>
<namePart type="family">Ballard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beena</namePart>
<namePart type="family">Ahmed</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>Guidelines are required for accurate and consistent transcription of speech corpora, especially when they contain more challenging, e.g. spontaneous or under-resourced speech. This paper presents a workflow and guidelines for transcribing spontaneous and under-resourced child speech in AusKidTalk, the first Australian English child corpus. Speech samples were elicited using a story-telling task and are 3.5 minutes long per child on average. Orthographic transcriptions were generated using automatic speech recognition (ASR) tools and corrected manually. A novel hand-correction protocol consisting of guidelines, hand-correction interface, and ground truth transcriptions together with consistency metrics were developed. Nine annotators submitted hand-corrections for 261 children’s story-telling task, and 25 ground truth tasks. Manual correction was 11-fold of speech time with a 3.5-minute-long story-telling task corrected in approximately 40 minutes. Efficiency is attributed to the quality of automatic transcription with 23% word error rate. Manual correction was accurate with annotators achieving consistent results on 15/25 ground truth submissions. Most inconsistent ground truth submissions were caused by a single, challenging ground truth task. These results show that our workflow yields efficient and accurate transcriptions, although transcriptions of potentially more challenging narrative tasks (e.g., elicited from younger children) might require further corrections.</abstract>
<identifier type="citekey">szalay-etal-2026-auskidtalk</identifier>
<identifier type="doi">10.63317/4j6otnjq8c3n</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.458/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5794</start>
<end>5804</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AusKidTalk: Developing Transcription Guidelines for Continuous Australian English Child Speech
%A Szalay, Tuende
%A Nan, Zheng
%A Huang, Renata
%A Shahin, Mostafa
%A Tharmakulasingam, Sirojan
%A Ballard, Kirrie
%A Ahmed, Beena
%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 szalay-etal-2026-auskidtalk
%X Guidelines are required for accurate and consistent transcription of speech corpora, especially when they contain more challenging, e.g. spontaneous or under-resourced speech. This paper presents a workflow and guidelines for transcribing spontaneous and under-resourced child speech in AusKidTalk, the first Australian English child corpus. Speech samples were elicited using a story-telling task and are 3.5 minutes long per child on average. Orthographic transcriptions were generated using automatic speech recognition (ASR) tools and corrected manually. A novel hand-correction protocol consisting of guidelines, hand-correction interface, and ground truth transcriptions together with consistency metrics were developed. Nine annotators submitted hand-corrections for 261 children’s story-telling task, and 25 ground truth tasks. Manual correction was 11-fold of speech time with a 3.5-minute-long story-telling task corrected in approximately 40 minutes. Efficiency is attributed to the quality of automatic transcription with 23% word error rate. Manual correction was accurate with annotators achieving consistent results on 15/25 ground truth submissions. Most inconsistent ground truth submissions were caused by a single, challenging ground truth task. These results show that our workflow yields efficient and accurate transcriptions, although transcriptions of potentially more challenging narrative tasks (e.g., elicited from younger children) might require further corrections.
%R 10.63317/4j6otnjq8c3n
%U https://aclanthology.org/2026.lrec-1.458/
%U https://doi.org/10.63317/4j6otnjq8c3n
%P 5794-5804
Markdown (Informal)
[AusKidTalk: Developing Transcription Guidelines for Continuous Australian English Child Speech](https://aclanthology.org/2026.lrec-1.458/) (Szalay et al., LREC 2026)
ACL