@inproceedings{matassoni-etal-2026-phonetic,
title = "Phonetic-based Ranking for Improved Pseudo-Labeling in Low-Resource {ASR}",
author = "Matassoni, Marco and
Gretter, Roberto and
Daniele, Falavigna and
Nawar, Mohamed Nabih Ali Mohamed and
Brutti, Alessio and
Negri, Matteo and
Cettolo, Mauro and
Gaido, Marco and
Papi, Sara and
Bentivogli, Luisa",
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-1.795/",
doi = "10.63317/338dnb8n7e85",
pages = "10130--10139",
abstract = "The rise of large language models has boosted speech and language technologies; however, where transcripts of audio data are limited, the performance of current technology is not yet satisfactory. One common strategy to tackle data scarcity is leveraging pseudo-labels, for example automatically transcribing data with a pre-trained ASR. One critical issue of this approach is assessing the quality of the automatic transcriptions, that may be rather bad for low-resourced languages. While several filtering approaches exist in literature, they typically work with decent pre-trained ASR models but may fail otherwise. In this work we propose a phonetic-based ranking, enabling an effective selection with controllable computational resources; the resulting subset of pseudo-labels serves as additional material for fine-tuning the source ASR models. Experiments on common benchmarks in three low-resource languages demonstrate the effectiveness of the proposed approach, yielding up to a 3-point reduction in WER."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="matassoni-etal-2026-phonetic">
<titleInfo>
<title>Phonetic-based Ranking for Improved Pseudo-Labeling in Low-Resource ASR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Matassoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Gretter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Falavigna</namePart>
<namePart type="family">Daniele</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Nabih</namePart>
<namePart type="given">Ali</namePart>
<namePart type="given">Mohamed</namePart>
<namePart type="family">Nawar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessio</namePart>
<namePart type="family">Brutti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mauro</namePart>
<namePart type="family">Cettolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Gaido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Papi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Bentivogli</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>The rise of large language models has boosted speech and language technologies; however, where transcripts of audio data are limited, the performance of current technology is not yet satisfactory. One common strategy to tackle data scarcity is leveraging pseudo-labels, for example automatically transcribing data with a pre-trained ASR. One critical issue of this approach is assessing the quality of the automatic transcriptions, that may be rather bad for low-resourced languages. While several filtering approaches exist in literature, they typically work with decent pre-trained ASR models but may fail otherwise. In this work we propose a phonetic-based ranking, enabling an effective selection with controllable computational resources; the resulting subset of pseudo-labels serves as additional material for fine-tuning the source ASR models. Experiments on common benchmarks in three low-resource languages demonstrate the effectiveness of the proposed approach, yielding up to a 3-point reduction in WER.</abstract>
<identifier type="citekey">matassoni-etal-2026-phonetic</identifier>
<identifier type="doi">10.63317/338dnb8n7e85</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.795/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10130</start>
<end>10139</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Phonetic-based Ranking for Improved Pseudo-Labeling in Low-Resource ASR
%A Matassoni, Marco
%A Gretter, Roberto
%A Daniele, Falavigna
%A Nawar, Mohamed Nabih Ali Mohamed
%A Brutti, Alessio
%A Negri, Matteo
%A Cettolo, Mauro
%A Gaido, Marco
%A Papi, Sara
%A Bentivogli, Luisa
%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 matassoni-etal-2026-phonetic
%X The rise of large language models has boosted speech and language technologies; however, where transcripts of audio data are limited, the performance of current technology is not yet satisfactory. One common strategy to tackle data scarcity is leveraging pseudo-labels, for example automatically transcribing data with a pre-trained ASR. One critical issue of this approach is assessing the quality of the automatic transcriptions, that may be rather bad for low-resourced languages. While several filtering approaches exist in literature, they typically work with decent pre-trained ASR models but may fail otherwise. In this work we propose a phonetic-based ranking, enabling an effective selection with controllable computational resources; the resulting subset of pseudo-labels serves as additional material for fine-tuning the source ASR models. Experiments on common benchmarks in three low-resource languages demonstrate the effectiveness of the proposed approach, yielding up to a 3-point reduction in WER.
%R 10.63317/338dnb8n7e85
%U https://aclanthology.org/2026.lrec-1.795/
%U https://doi.org/10.63317/338dnb8n7e85
%P 10130-10139
Markdown (Informal)
[Phonetic-based Ranking for Improved Pseudo-Labeling in Low-Resource ASR](https://aclanthology.org/2026.lrec-1.795/) (Matassoni et al., LREC 2026)
ACL
- Marco Matassoni, Roberto Gretter, Falavigna Daniele, Mohamed Nabih Ali Mohamed Nawar, Alessio Brutti, Matteo Negri, Mauro Cettolo, Marco Gaido, Sara Papi, and Luisa Bentivogli. 2026. Phonetic-based Ranking for Improved Pseudo-Labeling in Low-Resource ASR. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 10130–10139, Palma de Mallorca, Spain. ELRA Language Resource Association.