REDIT: Resilient Distributed Text-to-Speech at Edge Networks
REDIT: Resilient Distributed Text-to-Speech at Edge Networks
复制标题
DOI：
10.1109/globecom48099.2022.10001480
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Teng Li;H. Seferoglu;Erdem Koyuncu
中科院分区：
文献类型：
--
作者：
Teng Li;H. Seferoglu;Erdem Koyuncu
现有的基于深度学习的文本到语音（TTS）机制是计算密集型的，这给它们的实际应用带来了压力，特别是在由资源受限设备组成的边缘网络上。我们的重点是在多个设备上分配TTS任务（即，工作人员），并针对分散的工作人员提供TTS感知的弹性。特别是，我们设计了一个REsilient DIMENTTED TTS（REDIT）框架，利用文本摘要作为冗余，为分布式TTS提供弹性。我们分析表明，REDIT提高了任务完成时间相比，分布式TTS没有弹性。我们根据任务完成时间分析确定最佳的冗余/汇总量。我们实现了我们的REDIT框架在一个真实的测试平台组成的NVIDIA Jetson纳米卡，并表明，我们的REDIT算法改善了任务完成延迟相比，基线。
Existing deep learning-based Text-to-Speech (TTS) mechanisms are computationally intensive, which puts a strain in their practical applications especially over edge networks comprised of resource constrained devices. Our focus is on distributing TTS tasks across multiple devices (i.e., workers) at edge networks and providing TTS-aware resiliency against straggling workers. In particular, we design a REsilient DIstributed Tts (REDIT) framework by exploiting the text summarization as redundancy to provide resiliency for distributed TTS. We show analytically that REDIT improves the task completion time as compared to the distributed TTS without resiliency. We determine the optimum amount of redundancy/summary based on our task completion time analysis. We implement our REDIT framework in a real testbed consisting of NVIDIA Jetson Nano cards, and show that our REDIT algorithm improves the task completion delay as compared to baselines.