2 papers
cs.CL2026
When Does Predictor-Based RL Align with Human Perception? A Study of Subjective Rewards in Codec-Based Speech Language Models
Joonyong Park, Jerry Li
Codec-based text-to-speech (TTS) models make language-model post-training applicable to speech generation, but it remains unclear when learned perceptual predictors can serve as re…
cs.SD2026
AnimeScore: A Preference-Based Dataset and Framework for Evaluating Anime-Like Speech Style
Joonyong Park, Jerry Li
Evaluating 'anime-like' voices currently relies on costly subjective judgments, yet no standardized objective metric exists. A key challenge is that anime-likeness, unlike naturaln…