Year: 2026
Type: conference-paper
Abstract: Recent work reports gains in neural text-to-speech (TTS) with Group Relative Policy Optimization (GRPO). However, in the absence of a verifiable reward for prosody, GRPO trained on transcription-oriented signals (CER/NLL) lowers error rates yet collapses prosody into monotone, unnatural speech; adding speaker-similarity further destabilizes training and degrades CER. We address this with an iterative Direct Preference Optimization (DPO) scheme that uses only a few hundred human-labeled preference pairs per round to directly optimize prosodic naturalness while regularizing to the current model. On KoCC-TTS, a curated dataset of authentic Korean call center interactions capturing task-oriented dialogues, our method attains the highest human preference (ELO) with competitive CER, outperforming GRPO and strong commercial baselines. These results suggest that when prosody cannot be rewarded automatically, human preference optimization offers a practical and data-efficient path to natural and robust TTS. The demo page is available at https://tts.ch.dev.
Authors: Seungyoun Shin, Dongha Ahn, Jiwoo Kim, Sungwook Jeon
Institutions: Sungkyunkwan University, NAVER Cloud (South Korea)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416257939
FWCI:
Cites:
Cited by:
Related to: