HiGNN-TTS：面向表现力长文本语音合成的基于图神经网络的层级韵律建模
HiGNN-TTS: Hierarchical Prosody Modeling with Graph Neural Networks for Expressive Long-form TTS
AI总结：
针对长文本语音合成中高动态韵律建模的难题，提出HiGNN-TTS方法，通过引入虚拟全局节点、上下文注意力及层级监督拓展GNN建模能力，显著提升长文本合成语音的自然度与表现力。
摘要：
文本语音合成（TTS）领域的最新进展，尤其是基于图神经网络（GNNs）的方法，已显著提升了短文本合成语音的表现力。然而，生成具备高动态韵律变化、可与人类语音媲美的长文本语音仍具挑战性。为解决该问题，我们通过一种名为HiGNN-TTS的层级韵律建模方法拓展了GNNs的性能。具体而言，我们在图中添加了一个虚拟全局节点以增强词节点间的互连性，并引入上下文注意力机制，将GNNs的韵律建模范围从句内拓展至句间。此外，我们对图的每个节点施加来自声学韵律的层级监督，以捕捉高动态范围的韵律变化。消融实验验证了HiGNN-TTS在学习层级韵律方面的有效性。客观与主观评估均表明，HiGNN-TTS显著提升了长文本合成语音的自然度与表现力。
英文摘要：
Recent advances in text-to-speech, particularly those based on Graph Neural Networks (GNNs), have significantly improved the expressiveness of short-form synthetic speech. However, generating human-parity long-form speech with high dynamic prosodic variations is still challenging. To address this problem, we expand the capabilities of GNNs with a hierarchical prosody modeling approach, named HiGNN-TTS. Specifically, we add a virtual global node in the graph to strengthen the interconnection of word nodes and introduce a contextual attention mechanism to broaden the prosody modeling scope of GNNs from intra-sentence to inter-sentence. Additionally, we perform hierarchical supervision from acoustic prosody on each node of the graph to capture the prosodic variations with a high dynamic range. Ablation studies show the effectiveness of HiGNN-TTS in learning hierarchical prosody. Both objective and subjective evaluations demonstrate that HiGNN-TTS significantly improves the naturalness and expressiveness of long-form synthetic speech.
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。
