arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.16699eess.AScs.AIcs.LG
收藏

端到端零样本语音合成中无需超参数搜索的损失权衡自动调优

Automatic Tuning of Loss Trade-offs without Hyper-parameter Search in End-to-End Zero-Shot Speech Synthesis

CNAI;Institute for Convergence Research and Education in Advanced Technology, Yonsei University(延世大学先进技术融合研究与教育研究院);POSTECH(浦项科技大学)

Seongyeon Park, Bohyung Kim, Tae-hyun Oh

AI总结:

本文提出一种无需超参数搜索即可自动调优损失权衡的框架,通过诱导 VITS 解码器达到完全重建能力,在零样本 TTS 和 VC 中取得最先进性能并验证了鲁棒性。

摘要:

近年来,零样本 TTS 和 VC 方法因其能够在训练期间未见过的声音也能生成的实用性而受到关注。在这些方法中,VITS 模型的零样本改进版本表现出优越的性能,同时继承了 VITS 的有用特性。然而,VITS 及基于 VITS 的零样本模型的性能会因损失如何平衡而发生剧烈变化。这可能带来问题,因为它需要繁琐的损失平衡超参数调优过程来找到最优平衡。在这项工作中,我们提出了一个新的框架,通过诱导基于 VITS 模型的解码器达到其完全重建能力,从而无需搜索即可找到该最优值。借助我们的框架,我们在零样本 TTS 和 VC 中展示了优于基线的性能,达到了最先进的水平。此外,我们展示了该框架在各种设置下的鲁棒性。我们在讨论中对结果提供了解释。

英文摘要:

Recently, zero-shot TTS and VC methods have gained attention due to their practicality of being able to generate voices even unseen during training. Among these methods, zero-shot modifications of the VITS model have shown superior performance, while having useful properties inherited from VITS. However, the performance of VITS and VITS-based zero-shot models vary dramatically depending on how the losses are balanced. This can be problematic, as it requires a burdensome procedure of tuning loss balance hyper-parameters to find the optimal balance. In this work, we propose a novel framework that finds this optimum without search, by inducing the decoder of VITS-based models to its full reconstruction ability. With our framework, we show superior performance compared to baselines in zero-shot TTS and VC, achieving state-of-the-art performance. Furthermore, we show the robustness of our framework in various settings. We provide an explanation for the results in the discussion.

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。

↑