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 2003.12366eess.AScs.LGcs.SDstat.ML
收藏

在协处理器上训练语音识别模型

Training for Speech Recognition on Coprocessors

ITU(丹麦信息技术大学)

Sebastian Baunsgaard, Sebastian B. Wrede, Pınar Tozun

AI总结:

本文针对现代ASR系统训练效率缺乏详细分析的问题,构建基于深度神经网络的ASR模型,并在三类CPU-GPU协处理器平台评估,揭示硬件加速效果及建立ASR基准的重要性。

摘要:

近年来,自动语音识别(ASR)的 popularity 不断提升。处理器和存储技术的发展推动了更先进的 ASR 机制,进而促进了 Amazon Alexa、Apple Siri、Microsoft Cortana 和 Google Home 等虚拟助手的开发。这些助手的普及反过来又加速了 ASR 研究的新进展。然而,尽管 ASR 广受欢迎,现代 ASR 系统的训练效率分析却缺乏详细研究。这主要源于:许多依赖 ASR 的现代应用(如上述列举的应用)具有专有性质;用于加速 ASR 的协处理器硬件相对昂贵,大型厂商使用此类硬件来支持相关应用;以及缺乏成熟的基准测试。本文旨在解决后两个挑战。首先,本文描述了一个基于该领域最新研究的深度神经网络 ASR 模型,以及我们构建该模型的经验。然后,我们在代表不同预算类别的三个 CPU-GPU 协处理器平台上评估了该模型。结果表明,即使不使用高端设备,利用硬件加速也能取得良好效果。最昂贵的平台(价格是最便宜平台的 10 倍)达到初始精度目标的速度比其他两个平台快 10-30% 和 60-70%,但在精度目标略高时,各平台之间的差异几乎消失。此外,我们的结果进一步强调了由于 ASR 模型训练复杂、耗时且资源密集,评估 ASR 系统存在困难,同时也凸显了建立 ASR 基准测试的重要性。

英文摘要:

Automatic Speech Recognition (ASR) has increased in popularity in recent years. The evolution of processor and storage technologies has enabled more advanced ASR mechanisms, fueling the development of virtual assistants such as Amazon Alexa, Apple Siri, Microsoft Cortana, and Google Home. The interest in such assistants, in turn, has amplified the novel developments in ASR research. However, despite this popularity, there has not been a detailed training efficiency analysis of modern ASR systems. This mainly stems from: the proprietary nature of many modern applications that depend on ASR, like the ones listed above; the relatively expensive co-processor hardware that is used to accelerate ASR by big vendors to enable such applications; and the absence of well-established benchmarks. The goal of this paper is to address the latter two of these challenges. The paper first describes an ASR model, based on a deep neural network inspired by recent work in this domain, and our experiences building it. Then we evaluate this model on three CPU-GPU co-processor platforms that represent different budget categories. Our results demonstrate that utilizing hardware acceleration yields good results even without high-end equipment. While the most expensive platform (10X price of the least expensive one) converges to the initial accuracy target 10-30% and 60-70% faster than the other two, the differences among the platforms almost disappear at slightly higher accuracy targets. In addition, our results further highlight both the difficulty of evaluating ASR systems due to the complex, long, and resource intensive nature of the model training in this domain, and the importance of establishing benchmarks for ASR.

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。

↑