A Semi-Automatic Framework for Practical Transcription of Foreign Person Names in Lithuanian

Gailius Raškinis, Darius Amilevičius, Danguolė Kalinauskaitė, Artūras Mickus, Daiva Vitkutė-Adžgauskienė, Antanas Čenys and Tomas Krilavičius ()
Additional contact information
Gailius Raškinis: Faculty of Informatics, Vytautas Magnus University, Universiteto str. 10–202, Kaunas District, 53361 Akademija, Lithuania
Darius Amilevičius: Faculty of Informatics, Vytautas Magnus University, Universiteto str. 10–202, Kaunas District, 53361 Akademija, Lithuania
Danguolė Kalinauskaitė: Faculty of Informatics, Vytautas Magnus University, Universiteto str. 10–202, Kaunas District, 53361 Akademija, Lithuania
Artūras Mickus: Faculty of Informatics, Vytautas Magnus University, Universiteto str. 10–202, Kaunas District, 53361 Akademija, Lithuania
Daiva Vitkutė-Adžgauskienė: Faculty of Informatics, Vytautas Magnus University, Universiteto str. 10–202, Kaunas District, 53361 Akademija, Lithuania
Antanas Čenys: Department of Information Systems, Vilnius Gediminas Technical University, 10223 Vilnius, Lithuania
Tomas Krilavičius: Faculty of Informatics, Vytautas Magnus University, Universiteto str. 10–202, Kaunas District, 53361 Akademija, Lithuania

Mathematics, 2025, vol. 13, issue 13, 1-23

Abstract: We present a semi-automatic framework for transcribing foreign personal names into Lithuanian, aimed at reducing pronunciation errors in text-to-speech systems. Focusing on noisy, web-crawled data, the pipeline combines rule-based filtering, morphological normalization, and manual stress annotation—the only non-automated step—to generate training data for character-level transcription models. We evaluate three approaches: a weighted finite-state transducer (WFST), an LSTM-based sequence-to-sequence model with attention, and a Transformer model optimized for character transduction. Results show that word-pair models outperform single-word models, with the Transformer achieving the best performance (19.04% WER) on a cleaned and augmented dataset. Data augmentation via word order reversal proved effective, while combining single-word and word-pair training offered limited gains. Despite filtering, residual noise persists, with 54% of outputs showing some error, though only 11% were perceptually significant.

Keywords: practical transcription; character-level transduction; sequence-to-sequence learning; web-crawled data; Lithuanian (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/13/2107/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/13/2107/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:13:p:2107-:d:1688818

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().