标题： MPO：基于语言模型的文本到语音的多维偏好优化 显示英文标题

标题： MPO: Multidimensional Preference Optimization for Language Model-based Text-to-Speech

摘要： 近年来，通过大规模语言模型，文本到语音（TTS）取得了令人印象深刻的进展，实现了人类水平的语音质量。 整合人类反馈已被证明能有效提高这些系统的鲁棒性。 然而，当前方法在跨多个维度优化TTS时面临挑战，并且由于对奖励的过度自信，常常导致性能下降。 我们提出了多维偏好优化（MPO），以更好地使TTS系统与人类偏好对齐。 MPO引入了一个偏好集，简化了多维偏好优化的数据构建过程，实现了与多个维度的对齐。 此外，我们在训练过程中引入正则化，以解决基于DPO的方法中的典型退化问题。 我们的实验表明MPO的有效性，与基线系统相比，在可理解性、说话人相似性和韵律方面都有显著提升。 显示英文摘要

摘要： In recent years, text-to-speech (TTS) has seen impressive advancements through large-scale language models, achieving human-level speech quality. Integrating human feedback has proven effective for enhancing robustness in these systems. However, current approaches face challenges in optimizing TTS with preference data across multiple dimensions and often suffer from performance degradation due to overconfidence in rewards. We propose Multidimensional Preference Optimization (MPO) to better align TTS systems with human preferences. MPO introduces a preference set that streamlines the construction of data for multidimensional preference optimization, enabling alignment with multiple dimensions. Additionally, we incorporate regularization during training to address the typical degradation issues in DPO-based approaches. Our experiments demonstrate MPO's effectiveness, showing significant improvements in intelligibility, speaker similarity, and prosody compared to baseline systems.