利用句法与声学线索之间的相互作用优化韩语 TTS 停顿形成
Leveraging the Interplay Between Syntactic and Acoustic Cues for Optimizing Korean TTS Pause Formation
AI总结：
针对韩语 TPS 停顿错误问题，提出融合句法与声学线索的建模框架，在短音频训练下仍可稳定处理长而复杂的 OOD 句子。
摘要：
当代神经语音合成模型确实在合成语音生成方面展现出显著能力，其质量已达到可与人类生成语音相媲美的水平。然而，需要注意的是，这些成就主要是在英语等高资源语言语境中得到验证。此外，Tacotron 和 FastSpeech 的变体在应用于韩语时会出现严重的停顿错误，从而影响语音感知和自然度。为解决上述问题，我们提出了一种新颖框架，该框架对与停顿模式相关的句法线索和声学线索均进行全面建模。值得注意的是，尽管该框架是在短音频片段上训练的，但即使面对明显更长、更复杂的域外（OOD）句子，它也具备稳定生成自然语音的能力。通过与基线模型比较，并使用主观和客观指标开展消融研究，架构设计选择得到了验证，从而确认了模型性能。
英文摘要：
Contemporary neural speech synthesis models have indeed demonstrated remarkable proficiency in synthetic speech generation as they have attained a level of quality comparable to that of human-produced speech. Nevertheless, it is important to note that these achievements have predominantly been verified within the context of high-resource languages such as English. Furthermore, the Tacotron and FastSpeech variants show substantial pausing errors when applied to the Korean language, which affects speech perception and naturalness. In order to address the aforementioned issues, we propose a novel framework that incorporates comprehensive modeling of both syntactic and acoustic cues that are associated with pausing patterns. Remarkably, our framework possesses the capability to consistently generate natural speech even for considerably more extended and intricate out-of-domain (OOD) sentences, despite its training on short audio clips. Architectural design choices are validated through comparisons with baseline models and ablation studies using subjective and objective metrics, thus confirming model performance.
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。
