无需配对数据，直接优化语音合成中每个音素的自然度。
Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech
- 不依赖成对样本，直接在音素粒度上进行偏好优化。
- 日语语音合成错误率降低54%，发音准确率提升39%。
- 自动为关键音素赋予12.8倍更强奖励，适合高精度语音生成任务。
通过偏好优化对齐文本到语音（TTS）系统输出与人类反馈，已被证明能有效提升基于语言模型的TTS模型的鲁棒性和自然度。现有方法主要依赖于话语级别的理想与非理想样本配对，但此类配对在语音输出数据中往往稀缺，且话语级建模无法实现精确发音对齐所需的细粒度音素级优化。本研究提出TKTO方法，消除对配对数据的需求，实现更高效的数据利用，并直接针对音素级别单位进行优化，无需音素级标注即可自动提供细粒度对齐信号。实验表明，TKTO将挑战性的日语语音合成准确率提高39%，字符错误率（CER）降低54%，并自动为目标音素赋予12.8倍更强的奖励信号。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。