Preprint
Sep 2026
AlignDPO: Preference-Gated Alignment for Reducing Hallucination in Decoder-Only TTS
Decoder-only text-to-speech (TTS) models scale efficiently but remain prone to content hallucinations that arise from weak text-speech alignment during autoregressive generation. We find that robustness is governed by a non-monotone relation to the sharpness of the alignment-bearing attention heads: a moderate degree i...
Xiao Zhou, Oisín Turbitt, Kit Bower-Morris et al.
· 0 citations