@inproceedings{bystrich-etal-2026-selective,
title = "Selective Augmentation: Improving Universal Automatic Phonetic Transcription via {G}2{P} Bootstrapping",
author = "Bystrich, Tobias and
Pritzen, Julia Maria and
Schmidt, Christoph Andreas and
Wich-Reif, Claudia",
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-1.440/",
doi = "10.63317/53t62v2i3f8m",
pages = "5617--5624",
abstract = "In the field of universal automatic phonetic transcription (APT), clean and diverse training transcriptions are required. However, such high-quality data is limited. We propose the bootstrapping approach Selective Augmentation to improve the available training transcriptions by selectively transferring distinctions between languages. Based on the model MultIPA, we exemplarily show that we could increase the accuracy of an existing feature (plosive voicing) and add a new feature (plosive aspiration) by augmenting the existing training data using information from a separate helper language (Hindi). We describe intrinsic challenges of the evaluation and develop objective metrics to determine the success: Voicing accuracy was increased by 17.6{\%} by reducing the number of false positives. Additionally, aspiration recognition was introduced: While the baseline transcribed 0{\%} of German /p, t, k/ as aspirated, our approach transcribed them as aspirated in 61.2{\%} of the cases. Introducing aspiration recognition to APT models allowed for the tenuis class to be successfully reduced by 32.2{\%}, which also reduces the conflations between the test language{'}s plosives."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bystrich-etal-2026-selective">
<titleInfo>
<title>Selective Augmentation: Improving Universal Automatic Phonetic Transcription via G2P Bootstrapping</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tobias</namePart>
<namePart type="family">Bystrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Pritzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="given">Andreas</namePart>
<namePart type="family">Schmidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Wich-Reif</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>In the field of universal automatic phonetic transcription (APT), clean and diverse training transcriptions are required. However, such high-quality data is limited. We propose the bootstrapping approach Selective Augmentation to improve the available training transcriptions by selectively transferring distinctions between languages. Based on the model MultIPA, we exemplarily show that we could increase the accuracy of an existing feature (plosive voicing) and add a new feature (plosive aspiration) by augmenting the existing training data using information from a separate helper language (Hindi). We describe intrinsic challenges of the evaluation and develop objective metrics to determine the success: Voicing accuracy was increased by 17.6% by reducing the number of false positives. Additionally, aspiration recognition was introduced: While the baseline transcribed 0% of German /p, t, k/ as aspirated, our approach transcribed them as aspirated in 61.2% of the cases. Introducing aspiration recognition to APT models allowed for the tenuis class to be successfully reduced by 32.2%, which also reduces the conflations between the test language’s plosives.</abstract>
<identifier type="citekey">bystrich-etal-2026-selective</identifier>
<identifier type="doi">10.63317/53t62v2i3f8m</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.440/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5617</start>
<end>5624</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Selective Augmentation: Improving Universal Automatic Phonetic Transcription via G2P Bootstrapping
%A Bystrich, Tobias
%A Pritzen, Julia Maria
%A Schmidt, Christoph Andreas
%A Wich-Reif, Claudia
%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 bystrich-etal-2026-selective
%X In the field of universal automatic phonetic transcription (APT), clean and diverse training transcriptions are required. However, such high-quality data is limited. We propose the bootstrapping approach Selective Augmentation to improve the available training transcriptions by selectively transferring distinctions between languages. Based on the model MultIPA, we exemplarily show that we could increase the accuracy of an existing feature (plosive voicing) and add a new feature (plosive aspiration) by augmenting the existing training data using information from a separate helper language (Hindi). We describe intrinsic challenges of the evaluation and develop objective metrics to determine the success: Voicing accuracy was increased by 17.6% by reducing the number of false positives. Additionally, aspiration recognition was introduced: While the baseline transcribed 0% of German /p, t, k/ as aspirated, our approach transcribed them as aspirated in 61.2% of the cases. Introducing aspiration recognition to APT models allowed for the tenuis class to be successfully reduced by 32.2%, which also reduces the conflations between the test language’s plosives.
%R 10.63317/53t62v2i3f8m
%U https://aclanthology.org/2026.lrec-1.440/
%U https://doi.org/10.63317/53t62v2i3f8m
%P 5617-5624
Markdown (Informal)
[Selective Augmentation: Improving Universal Automatic Phonetic Transcription via G2P Bootstrapping](https://aclanthology.org/2026.lrec-1.440/) (Bystrich et al., LREC 2026)
ACL