Increasing the robustness of CNN acoustic models using autoregressive moving average spectrogram features and channel dropout-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Increasing the robustness of CNN acoustic models using autoregressive moving average spectrogram features and channel dropout

Published:2017-12 Issue: Volume:100 Page:44-50
ISSN:0167-8655
Container-title:Pattern Recognition Letters
language:en
Short-container-title:Pattern Recognition Letters

Author:

Kovács György,Tóth László,Van Compernolle Dirk,Ganapathy Sriram

Publisher

Elsevier BV

Subject

Artificial Intelligence,Computer Vision and Pattern Recognition,Signal Processing,Software

Reference32 articles.

1. Convolutional neural networks for speech recognition;Abdel-Hamid;IEEE/ACM Trans. ASLP,2014

2. How do humans process and recognize speech?;Allen;IEEE Trans. on Speech and Audio Proc.,1994

3. Exemplar-based speech enhancement for deep neural network based automatic speech recognition;Baby,2015

4. A new ASR approach based on independent processing and recombination of partial frequency bands;Bourlard,1996

5. Dropout as data augmentation;Bouthillier;ArXiv e-prints,2015

Cited by 32 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. Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models;2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN);2023-08-28

2. Detection of various lung diseases including COVID-19 using extreme learning machine algorithm based on the features extracted from a lightweight CNN architecture;Biocybernetics and Biomedical Engineering;2023-07

3. ChestX-Ray6: Prediction of multiple diseases including COVID-19 from chest X-ray images using convolutional neural network;Expert Systems with Applications;2023-01

4. Diagnosis of Malaria Using Double Hidden Layer Extreme Learning Machine Algorithm With CNN Feature Extraction and Parasite Inflator;IEEE Access;2023

5. Cough Sound Analysis for the Evidence of Covid-19;Computer Vision and Machine Intelligence;2023

同舟云学术

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