Evaluating Robustness to Noise and Compression of Deep Neural Networks for Keyword Spotting
Author:
Affiliation:
1. Department of Electronic Systems Engineering, Escola Politécnica, University of São Paulo, São Paulo, Brazil
Funder
Coordenaçao de Aperfeiçoamento de Pessoal de Nível Superior
Fundaçao de Amparo à Pesquisa do Estado de S ao Paulo
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
General Engineering,General Materials Science,General Computer Science,Electrical and Electronic Engineering
Link
http://xplorestaging.ieee.org/ielx7/6287639/10005208/10136724.pdf?arnumber=10136724
Reference59 articles.
1. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and ¡0.5MB model size;iandola;arXiv 1602 07360,2016
2. Wav2Vec 2.0: A framework for self-supervised learning of speech representations;baevski;Proc 34th Int Conf Neural Inf Process Syst,2020
3. Noisy Student-Teacher Training for Robust Keyword Spotting
4. Wav2KWS: Transfer Learning From Speech Representations for Keyword Spotting
5. EfficientNet: Rethinking model scaling for convolutional neural networks;tan;Proc Int Conf Mach Learn,2019
Cited by 2 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. Advantages and Pitfalls of Dataset Condensation: An Approach to Keyword Spotting with Time-Frequency Representations;Electronics;2024-05-28
2. Efficient Real-Time Smart Keyword Spotting Using Spectrogram-Based Hybrid CNN-LSTM for Edge System;IEEE Access;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