基于自训练的逐帧呼吸检测：提升文本转语音中呼吸自然度的探索
Frame-Wise Breath Detection with Self-Training: An Exploration of Enhancing Breath Naturalness in Text-to-Speech
AI总结：
针对 TTS 中呼吸位置人工标注成本高的问题，提出结合规则初标与伪标签自训练的 Conformer 逐帧呼吸检测模型，并在多说话人 TTS 中验证其可提升呼吸合成自然度。
摘要：
开发能够合成自然呼吸的文本转语音（TTS）系统对于类人语音智能体至关重要，但这需要对训练数据中的呼吸位置进行大量人工标注。为此，我们提出了一种自训练方法，用于训练能够自动检测语音中呼吸位置的呼吸检测模型。我们的方法使用大型语音语料库训练模型，包括：1）利用基于规则的方法标注有限的呼吸声，2）通过基于模型预测的伪标签迭代扩充这些标注。我们的检测模型采用带有下采样/上采样层的 Conformer 块，实现准确的逐帧呼吸检测。我们使用带有检测到的呼吸标记的文本转写，研究了其在多说话人 TTS 中的有效性。结果表明，使用我们提出的模型进行呼吸检测和呼吸标记插入，比基线模型能更自然地合成包含呼吸的语音。
英文摘要：
Developing Text-to-Speech (TTS) systems that can synthesize natural breath is essential for human-like voice agents but requires extensive manual annotation of breath positions in training data. To this end, we propose a self-training method for training a breath detection model that can automatically detect breath positions in speech. Our method trains the model using a large speech corpus and involves: 1) annotation of limited breath sounds utilizing a rule-based approach, and 2) iterative augmentation of these annotations through pseudo-labeling based on the model's predictions. Our detection model employs Conformer blocks with down-/up-sampling layers, enabling accurate frame-wise breath detection. We investigate its effectiveness in multi-speaker TTS using text transcripts with detected breath marks. The results indicate that using our proposed model for breath detection and breath mark insertion synthesizes breath-contained speech more naturally than a baseline model.
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。
