arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.08795cs.LG
收藏

基于动态Transformer的联邦学习在文语转换中的应用

Federated Learning with Dynamic Transformer for Text to Speech

Ping An Technology (Shenzhen) Co., Ltd.(平安科技(深圳)有限公司)

Zhenhou Hong, Jianzong Wang, Xiaoyang Qu, Jie Liu, Chendong Zhao, Jing Xiao

摘要:

文本到语音(TTS)是用户交互的关键任务,但TTS模型训练依赖于大量高质量的原始数据集。由于隐私和安全问题,原始数据集通常无法直接使用。最近,联邦学习提出了一种流行的分布式机器学习范式,具有增强的隐私保护机制。它为数据所有者提供了一个实用而安全的框架,以便与其他人合作,从而获得在更大数据集上训练的更好的全局模型。然而,由于Transformer模型的高度复杂性,在联邦学习设置中,收敛过程变得缓慢且不稳定。此外,在联邦学习中训练的Transformer模型是昂贵的通信和有限的客户端计算速度,阻碍了其普及。为了应对这些挑战,我们提出了联邦动态Transformer。一方面,与联邦transformer Transformer相比,性能有了很大的提高,随着客户端数量的增加,性能接近集中训练的transformer-TTS。另一方面,它在训练阶段实现了更快,更稳定的收敛,并显着减少了通信时间。在LJSpeech数据集上的实验也有力地证明了该方法的优越性。

英文摘要:

Text to speech (TTS) is a crucial task for user interaction, but TTS model training relies on a sizable set of high-quality original datasets. Due to privacy and security issues, the original datasets are usually unavailable directly. Recently, federated learning proposes a popular distributed machine learning paradigm with an enhanced privacy protection mechanism. It offers a practical and secure framework for data owners to collaborate with others, thus obtaining a better global model trained on the larger dataset. However, due to the high complexity of transformer models, the convergence process becomes slow and unstable in the federated learning setting. Besides, the transformer model trained in federated learning is costly communication and limited computational speed on clients, impeding its popularity. To deal with these challenges, we propose the federated dynamic transformer. On the one hand, the performance is greatly improved comparing with the federated transformer, approaching centralize-trained Transformer-TTS when increasing clients number. On the other hand, it achieves faster and more stable convergence in the training phase and significantly reduces communication time. Experiments on the LJSpeech dataset also strongly prove our method's advantage.

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。

↑