论文标题
在低能低复杂平台上进行声学事件检测的紧凑型复发网络
Compact recurrent neural networks for acoustic event detection on low-energy low-complexity platforms
论文作者
论文摘要
户外声学事件检测是一个令人兴奋的研究领域，但受到对复杂算法和深度学习技术的需求的挑战，通常需要许多计算，记忆和能源。这项挑战阻碍了物联网实施，其中需要有效利用资源。但是，当前的嵌入式技术和微控制器可以提高其能力，而无需惩罚能源效率。本文通过在物联网的资源约束嵌入式平台上优化了边缘的声音事件检测的应用。贡献是两个方面的：首先，提出了两阶段的学生教师方法，以使最新的神经网络用于当前的微控制器，以进行声音事件检测；其次，我们在ARM皮层M4上测试我们的方法，尤其是针对与8位量化有关的问题。我们的嵌入式实现可以在urbansound8k上获得68％的准确性，距离最先进的性能不远，每秒音频流的推理时间为125毫秒，并且仅在34.3 kb的RAM中为5.5 MW的功率消耗。
Outdoor acoustic events detection is an exciting research field but challenged by the need for complex algorithms and deep learning techniques, typically requiring many computational, memory, and energy resources. This challenge discourages IoT implementation, where an efficient use of resources is required. However, current embedded technologies and microcontrollers have increased their capabilities without penalizing energy efficiency. This paper addresses the application of sound event detection at the edge, by optimizing deep learning techniques on resource-constrained embedded platforms for the IoT. The contribution is two-fold: firstly, a two-stage student-teacher approach is presented to make state-of-the-art neural networks for sound event detection fit on current microcontrollers; secondly, we test our approach on an ARM Cortex M4, particularly focusing on issues related to 8-bits quantization. Our embedded implementation can achieve 68% accuracy in recognition on Urbansound8k, not far from state-of-the-art performance, with an inference time of 125 ms for each second of the audio stream, and power consumption of 5.5 mW in just 34.3 kB of RAM.
