works on
multilingual speech recognition 1reinforcement learning adaptation 1speaker diarization 1synthetic speech augmentation 1two-speaker conversation 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing eess.ASShow all

1 paper · 1 filter

eess.AS2026

FNH-TTS: Mixture-of-Experts Duration Modeling for Robust Neural Speech Synthesis

Qingliang Meng, Yuqing Deng, Wei Liang +3

Current non-autoregressive (NAR) text-to-speech (TTS) systems still struggle to model diverse and speaker-dependent duration variation. We further observe that richer duration vari…