3 papers
cs.LG2026
GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech
Antonis Asonitis, Francesco Verdini, Aref Farhadipour +4
We present GRAFT, a per-word pronunciation conditioning mechanism for text-to-speech neural codec language modeling. Existing systems reach high intelligibility and naturalness but…
cs.LG2026
Post-Training Speech Enhancement Language Models with Perceptual Rewards
Frédéric Berdoz, Luca A. Lanzendörfer, Antonis Asonitis +1
Speech enhancement language models achieve strong results when trained on discrete audio tokens, but their optimization relies on token-level cross-entropy rather than the perceptu…
cs.SD2025
High-Fidelity Speech Enhancement via Discrete Audio Tokens
Luca A. Lanzendörfer, Frédéric Berdoz, Antonis Asonitis +1
Recent autoregressive transformer-based speech enhancement (SE) methods have shown promising results by leveraging advanced semantic understanding and contextual modeling of speech…