{"ID":2875025,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.03300","arxiv_id":"2509.03300","title":"LatPhon: Lightweight Multilingual G2P for Romance Languages and English","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.","short_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--En...","url_abs":"https://arxiv.org/abs/2509.03300","url_pdf":"https://arxiv.org/pdf/2509.03300v1","authors":"[\"Luis Felipe Chary\",\"Miguel Arjona Ramirez\"]","published":"2025-09-03T13:25:44Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Transformer\"]","has_code":false}