多语言韵律迁移：监督学习与迁移学习的比较
Multilingual Prosody Transfer: Comparing Supervised & Transfer Learning
AI总结：
本研究对比监督微调与迁移学习两种适配预训练单语TTS模型至多语言场景的方法，通过MOS、RA、MCD三项指标验证，发现迁移学习性能更优，可为低资源语言TTS模型构建提供支撑。
摘要：
语音合成系统中的韵律迁移领域正在快速发展。本研究聚焦于评估将预训练单语语音合成（TTS）模型适配至多语言场景的学习方法，即监督微调（Supervised Fine-Tuning, SFT）与迁移学习（Transfer Learning, TL）。本次比较采用三项不同指标：平均意见得分（MOS）、识别准确率（RA）以及梅尔倒谱失真（MCD）。结果表明，与SFT相比，TL带来了显著提升的性能，平均MOS高出1.53分，RA提升37.5%，MCD改善约7.8点。这些发现对构建低资源语言的TTS模型具有重要帮助。
英文摘要：
The field of prosody transfer in speech synthesis systems is rapidly advancing. This research is focused on evaluating learning methods for adapting pre-trained monolingual text-to-speech (TTS) models to multilingual conditions, i.e., Supervised Fine-Tuning (SFT) and Transfer Learning (TL). This comparison utilizes three distinct metrics: Mean Opinion Score (MOS), Recognition Accuracy (RA), and Mel Cepstral Distortion (MCD). Results demonstrate that, in comparison to SFT, TL leads to significantly enhanced performance, with an average MOS higher by 1.53 points, a 37.5% increase in RA, and approximately a 7.8-point improvement in MCD. These findings are instrumental in helping build TTS models for low-resource languages.
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。
