Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915960153178112 |
|---|---|
| author | Kotoge, Rikuto Sasaki, Yuichi |
| author_facet | Kotoge, Rikuto Sasaki, Yuichi |
| contents | Aligning text-to-speech (TTS) system outputs with human feedback through preference optimization has been shown to effectively improve the robustness and naturalness of language model-based TTS models. Current approaches primarily require paired desirable and undesirable samples at the utterance level. However, such pairs are often limited in TTS output data, and utterance-level formulation prevents fine-grained token-level optimization needed for accurate pronunciation alignment. In this study, we propose TKTO that eliminates the need for paired data, enabling a more data-efficient training paradigm, and directly targets token-level units, automatically providing fine-grained alignment signals without token-level annotations. TKTO improves the challenging Japanese TTS accuracy by 39% and reduces CER by 54%, automatically assigning 12.8 times stronger reward to targeted tokens. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_05799 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech Kotoge, Rikuto Sasaki, Yuichi Computation and Language Artificial Intelligence Sound Aligning text-to-speech (TTS) system outputs with human feedback through preference optimization has been shown to effectively improve the robustness and naturalness of language model-based TTS models. Current approaches primarily require paired desirable and undesirable samples at the utterance level. However, such pairs are often limited in TTS output data, and utterance-level formulation prevents fine-grained token-level optimization needed for accurate pronunciation alignment. In this study, we propose TKTO that eliminates the need for paired data, enabling a more data-efficient training paradigm, and directly targets token-level units, automatically providing fine-grained alignment signals without token-level annotations. TKTO improves the challenging Japanese TTS accuracy by 39% and reduces CER by 54%, automatically assigning 12.8 times stronger reward to targeted tokens. |
| title | Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech |
| topic | Computation and Language Artificial Intelligence Sound |
| url | https://arxiv.org/abs/2510.05799 |