Showing cs.CLShow all
2 papers · 1 filter
cs.CL2025
LatinX: Aligning a Multilingual TTS Model with Direct Preference Optimization
Luis Felipe Chary, Miguel Arjona Ramirez
We present LatinX, a multilingual text-to-speech (TTS) model for cascaded speech-to-speech translation that preserves the source speaker's identity across languages. LatinX is a 12…
cs.CL2025
LatPhon: Lightweight Multilingual G2P for Romance Languages and English
Luis Felipe Chary, Miguel Arjona Ramirez
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, esp…