Phonetic-based Ranking for Improved Pseudo-Labeling in Low-Resource ASR

Marco Matassoni, Roberto Gretter, Falavigna Daniele, Mohamed Nabih Ali Mohamed Nawar, Alessio Brutti, Matteo Negri, Mauro Cettolo, Marco Gaido, Sara Papi, Luisa Bentivogli


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.
Anthology ID:
2026.lrec-1.795
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
10130–10139
Language:
External URL:
https://lrec.elra.info/lrec2026-main-795
DOI:
10.63317/338dnb8n7e85
Bibkey:
Cite (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.
Cite (Informal):
Phonetic-based Ranking for Improved Pseudo-Labeling in Low-Resource ASR (Matassoni et al., LREC 2026)
Copy Citation: