Selective Augmentation: Improving Universal Automatic Phonetic Transcription via G2P Bootstrapping

Tobias Bystrich, Julia Maria Pritzen, Christoph Andreas Schmidt, Claudia Wich-Reif


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.
Anthology ID:
2026.lrec-1.440
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:
5617–5624
Language:
External URL:
https://lrec.elra.info/lrec2026-main-440
DOI:
10.63317/53t62v2i3f8m
Bibkey:
Cite (ACL):
Tobias Bystrich, Julia Maria Pritzen, Christoph Andreas Schmidt, and Claudia Wich-Reif. 2026. Selective Augmentation: Improving Universal Automatic Phonetic Transcription via G2P Bootstrapping. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5617–5624, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Selective Augmentation: Improving Universal Automatic Phonetic Transcription via G2P Bootstrapping (Bystrich et al., LREC 2026)
Copy Citation: