2 papers
eess.AS2026
AlignDPO: Preference-Gated Alignment for Reducing Hallucination in Decoder-Only TTS
Xiao Zhou, Oisín Turbitt, Kit Bower-Morris +3
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. W…
cs.SD2025
Whilter: A Whisper-based Data Filter for "In-the-Wild" Speech Corpora Using Utterance-level Multi-Task Classification
William Ravenscroft, George Close, Kit Bower-Morris +3
Large-scale in-the-wild speech datasets have become more prevalent in recent years due to increased interest in models that can learn useful features from unlabelled data for tasks…