声音事件检测系统的能耗趋势
Energy Consumption Trends in Sound Event Detection Systems
AI总结:
本文针对深度学习系统能耗攀升的问题,分析了DCASE挑战赛引入的SED系统能耗评估准则的影响,发现训练阶段节能方法兴起且性能未降,但运算量与复杂度仍增长,旨在推动领域环保实践。
摘要:
深度学习系统的能耗与计算密集度持续攀升,引发了人们对其环境影响的担忧。作为声学场景与事件检测与分类(Detection and Classification of Acoustic Scenes and Events, DCASE)挑战赛的主办方,我们深知解决这一问题的重要性。过去三年间,我们已将能耗指标纳入声音事件检测(sound event detection, SED)系统的评估体系。本文分析了该能耗准则对挑战赛结果的影响,并探究了多年来系统复杂度与能耗的演变情况。我们发现,研究方向正转向训练阶段更节能的方法,且未牺牲性能,但运算量与系统复杂度仍在持续增长。通过本次分析,我们希望在SED领域推动更环保的实践方式。
英文摘要:
Deep learning systems have become increasingly energy- and computation-intensive, raising concerns about their environmental impact. As organizers of the Detection and Classification of Acoustic Scenes and Events (DCASE) challenge, we recognize the importance of addressing this issue. For the past three years, we have integrated energy consumption metrics into the evaluation of sound event detection (SED) systems. In this paper, we analyze the impact of this energy criterion on the challenge results and explore the evolution of system complexity and energy consumption over the years. We highlight a shift towards more energy-efficient approaches during training without compromising performance, while the number of operations and system complexity continue to grow. Through this analysis, we hope to promote more environmentally friendly practices within the SED community.
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。