CosyAccent: 基于源合成训练数据的可控声调规范化
CosyAccent: Duration-Controllable Accent Normalization Using Source-Synthesis Training Data
AI总结：
CosyAccent通过源合成训练数据构建方法，实现可控的声调规范化，无需真实L2数据，提升内容保持与自然度。
摘要：
声调规范化（AN）系统常面临不自然的输出和不必要的内容失真，这源于训练数据不足和持续时间建模僵化。本文提出了一种
英文摘要：
Accent normalization (AN) systems often struggle with unnatural outputs and undesired content distortion, stemming from both suboptimal training data and rigid duration modeling. In this paper, we propose a "source-synthesis" methodology for training data construction. By generating source L2 speech and using authentic native speech as the training target, our approach avoids learning from TTS artifacts and, crucially, requires no real L2 data in training. Alongside this data strategy, we introduce CosyAccent, a non-autoregressive model that resolves the trade-off between prosodic naturalness and duration control. CosyAccent implicitly models rhythm for flexibility yet offers explicit control over total output duration. Experiments show that, despite being trained without any real L2 speech, CosyAccent achieves significantly improved content preservation and superior naturalness compared to strong baselines trained on real-world data.
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。
