English

LatPhon: Lightweight Multilingual G2P for Romance Languages and English

Computation and Language 2025-09-04 v1

Abstract

Grapheme-to-phoneme (G2P) conversion is a key front-end for text-to-speech (TTS), automatic speech recognition (ASR), speech-to-speech translation (S2ST) and alignment systems, especially across multiple Latin-script languages.We present LatPhon, a 7.5 M - parameter Transformer jointly trained on six such languages--English, Spanish, French, Italian, Portuguese, and Romanian. On the public ipa-dict corpus, it attains a mean phoneme error rate (PER) of 3.5%, outperforming the byte-level ByT5 baseline (5.4%) and approaching language-specific WFSTs (3.2%) while occupying 30 MB of memory, which makes on-device deployment feasible when needed. These results indicate that compact multilingual G2P can serve as a universal front-end for Latin-language speech pipelines.

Keywords

Cite

@article{arxiv.2509.03300,
  title  = {LatPhon: Lightweight Multilingual G2P for Romance Languages and English},
  author = {Luis Felipe Chary and Miguel Arjona Ramirez},
  journal= {arXiv preprint arXiv:2509.03300},
  year   = {2025}
}