Bengu Wu

A preference optimization framework with Large Audio-Language Model (LALM) feedback for controllable non-verbal vocalization (NVV) generation in continuous autoregressive speech models that enables DPO-style preference learning without explicit sequence likelihoods while preserving direct supervision on preferred realizations is proposed.

Open-source TTS models can beat commercial systems in specific languages, but current instruction-following TTS still struggles with complex instructions like nuanced paralinguistic controls.