合成Lombard效应：TTS中语音清晰度和发声努力的多级控制
Synthesizing the Lombard Effect: Multi-Level Control of Speech Clarity and Vocal Effort in TTS
AI总结：
提出基于流匹配的TTS模型，利用发声努力和发音伪标签实现连续解耦控制及词级强调，模拟Lombard效应，提升嘈杂环境下的语音清晰度。
摘要：
人类在具有挑战性的环境中（如嘈杂条件或与听障听众交流时）倾向于更大声、更清晰地说话，这被称为Lombard效应。为了在语音合成系统中模拟这种行为，我们引入了一个基于流匹配的文本到语音（TTS）模型，该模型使用发声努力和发音伪标签进行训练。所提出的模型实现了发声努力和发音的连续且解耦的控制，同时还能够实现词级强调以澄清话语的特定片段。实验结果表明，这些控制机制有效改善了与清晰度相关的声学特征。此外，噪声中的语音实验表明，我们的模型成功模拟了人类清晰语音在嘈杂条件下的可懂度提升。
英文摘要：
Humans tend to speak louder and clearer in challenging environments, such as noisy conditions or when addressing hearingimpaired listeners, which is called Lombard effect. To simulate this behavior in speech synthesis systems, we introduce a flow-matching based text-to-speech (TTS) model trained with vocal effort and articulation pseudo-labels. The proposed model achieves continuous and disentangled control of vocal effort and articulation, while also enabling word-level emphasis for clarifying specific segments of an utterance. Experimental results show that these control mechanisms effectively improve clarityrelated acoustic features. Furthermore, speech-in-noise experiments demonstrate that our model successfully simulates the intelligibility gains of human clear speech in noisy conditions.
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。
