DiffEditor：通过语义增强与声学一致性提升语音编辑
DiffEditor: Enhancing Speech Editing with Semantic Enrichment and Acoustic Consistency
AI总结：
本文提出DiffEditor语音编辑模型，通过整合预训练语言模型词嵌入增强语义信息，并引入一阶损失函数优化帧间平滑，显著提升了领域外文本编辑的可懂度、声学一致性与流畅度。
摘要：
随着基于文本的语音编辑日益普及，对不受限制的自由文本编辑的需求不断增长。然而，现有的语音编辑技术在处理领域外（OOD）文本时面临重大挑战，特别是在保持可懂度和声学一致性方面。在本文中，我们提出了DiffEditor，一种新型语音编辑模型，旨在通过语义增强和声学一致性提升OOD文本场景下的性能。为提高编辑语音的可懂度，我们通过整合从预训练语言模型中提取的词嵌入来丰富音素嵌入的语义信息。此外，我们强调帧间平滑特性对于建模声学一致性至关重要，因此提出了一阶损失函数，以促进编辑边界处更平滑的过渡并增强编辑语音的整体流畅度。实验结果表明，我们的模型在领域内和OOD文本场景中均取得了最先进的性能。
英文摘要：
As text-based speech editing becomes increasingly prevalent, the demand for unrestricted free-text editing continues to grow. However, existing speech editing techniques encounter significant challenges, particularly in maintaining intelligibility and acoustic consistency when dealing with out-of-domain (OOD) text. In this paper, we introduce, DiffEditor, a novel speech editing model designed to enhance performance in OOD text scenarios through semantic enrichment and acoustic consistency. To improve the intelligibility of the edited speech, we enrich the semantic information of phoneme embeddings by integrating word embeddings extracted from a pretrained language model. Furthermore, we emphasize that interframe smoothing properties are critical for modeling acoustic consistency, and thus we propose a first-order loss function to promote smoother transitions at editing boundaries and enhance the overall fluency of the edited speech. Experimental results demonstrate that our model achieves state-of-the-art performance in both in-domain and OOD text scenarios.
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。
