利用人类反馈增强零样本文本到语音合成
Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback
AI总结：
本文提出一种基于人类反馈的采样-标注-学习框架UNO，通过直接最大化语音生成效用并考虑主观感知不确定性，显著提升了TTS模型的零样本性能及情感风格适应能力。
摘要：
近年来，文本到语音（TTS）技术取得了显著进展，特别是在大规模训练数据集的推动下，展现出人类水平的语音质量以及对未见说话者的出色零样本能力。然而，尽管诸如平均主观意见分（MOS）等人类主观评估仍然是评估合成语音质量的黄金标准，但即使是最先进的TTS方法也将人类反馈与训练隔离，导致训练目标与评估指标不匹配。在本研究中，我们探讨了将主观人类评估整合到TTS训练循环中的新课题。受基于人类反馈的强化学习近期成功的启发，我们提出了一种专为TTS优化量身定制的综合采样-标注-学习框架，即不确定性感知优化（UNO）。具体而言，UNO通过直接最大化语音生成的效用，同时考虑主观人类语音感知和评估内在变异性中存在的不确定性，从而消除了对奖励模型或偏好数据的需求。主观和客观评估的实验结果表明，UNO在MOS、词错误率和说话者相似度方面显著提升了TTS模型的零样本性能。此外，我们还展示了UNO的一项卓越能力，即它能够无缝且灵活地适应情感TTS中所需的说话风格。
英文摘要：
In recent years, text-to-speech (TTS) technology has witnessed impressive advancements, particularly with large-scale training datasets, showcasing human-level speech quality and impressive zero-shot capabilities on unseen speakers. However, despite human subjective evaluations, such as the mean opinion score (MOS), remaining the gold standard for assessing the quality of synthetic speech, even state-of-the-art TTS approaches have kept human feedback isolated from training that resulted in mismatched training objectives and evaluation metrics. In this work, we investigate a novel topic of integrating subjective human evaluation into the TTS training loop. Inspired by the recent success of reinforcement learning from human feedback, we propose a comprehensive sampling-annotating-learning framework tailored to TTS optimization, namely uncertainty-aware optimization (UNO). Specifically, UNO eliminates the need for a reward model or preference data by directly maximizing the utility of speech generations while considering the uncertainty that lies in the inherent variability in subjective human speech perception and evaluations. Experimental results of both subjective and objective evaluations demonstrate that UNO considerably improves the zero-shot performance of TTS models in terms of MOS, word error rate, and speaker similarity. Additionally, we present a remarkable ability of UNO that it can adapt to the desired speaking style in emotional TTS seamlessly and flexibly.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
