Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks
Author:
Affiliation:
1. ICT-irst Fondazione Bruno Kessler, Trento, Italy
2. Computing Systems Laboratory, Huawei Technologies, Zürich Research Center, Zürich, Switzerland
3. Department of Electrical Engineering and Information Technology, ETH Zürich, Zürich, Switzerland
Funder
European Union’s Horizon 2020 Research and Innovation Program
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Electrical and Electronic Engineering
Link
http://xplorestaging.ieee.org/ielx7/8919/9763566/09707596.pdf?arnumber=9707596
Reference52 articles.
1. NS-FDN: Near-Sensor Processing Architecture of Feature-Configurable Distributed Network for Beyond-Real-Time Always-on Keyword Spotting
2. Fully integrated 500uW speech detection wake-up circuit
3. Compact Recurrent Neural Networks for Acoustic Event Detection on Low-Energy Low-Complexity Platforms
4. Efficient convolutional neural network for audio event detection;meyer;arXiv 1709 09888,2017
5. An Optimized Recurrent Unit for Ultra-Low-Power Keyword Spotting
Cited by 13 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. xTern: Energy-Efficient Ternary Neural Network Inference on RISC-V-Based Edge Systems;2024 IEEE 35th International Conference on Application-specific Systems, Architectures and Processors (ASAP);2024-07-24
2. Advantages and Pitfalls of Dataset Condensation: An Approach to Keyword Spotting with Time-Frequency Representations;Electronics;2024-05-28
3. Memristor Synapse-Driven Simplified Hopfield Neural Network: Hidden Dynamics, Attractor Control, and Circuit Implementation;IEEE Transactions on Circuits and Systems I: Regular Papers;2024-05
4. In‐Sensor Passive Speech Classification with Phononic Metamaterials;Advanced Functional Materials;2024-01-09
5. A Memcapacitor Biomimetic Circuit Realizing Classical Conditioning and Fear Learning;IEEE Transactions on Circuits and Systems I: Regular Papers;2024
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3