GPU-based fast signal processing for large amounts of snore sound data

Jian Guo, Kun Qian, Huijie Xu, Christoph Janott, Bjorn Schuller, Satoshi Matsuoka

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

Snore sound (SnS) data has been demonstrated to carry very important information for diagnosis and evaluation of sleep related breathing disorders with high prevalence, such as Primary Snoring and Obstructive Sleep Apnea (OSA) - a serious chronic sleep disorder with a big community. With the increasing number of collected SnS data from subjects, how to handle such large amount of data is a big challenge, and a huge opportunity for further study on optimally combining signal processing techniques with machine learning algorithms. In this study, we utilize the Graphics Processing Unit (GPU) to process a large amount of SnS data collected from hospitals in Germany (37 subjects, 38.34 hours, 15.10 GB). Experimental results prove that, our GPU-based platform significantly speeds up the audio processing for features extraction of SnS data, compared with the traditional Central Processing Unit (CPU) system.

源语言英语
主期刊名2016 IEEE 5th Global Conference on Consumer Electronics, GCCE 2016
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781509023332
DOI
出版状态已出版 - 27 12月 2016
已对外发布
活动5th IEEE Global Conference on Consumer Electronics, GCCE 2016 - Kyoto, 日本
期限: 11 10月 201614 10月 2016

出版系列

姓名2016 IEEE 5th Global Conference on Consumer Electronics, GCCE 2016

会议

会议5th IEEE Global Conference on Consumer Electronics, GCCE 2016
国家/地区日本
Kyoto
时期11/10/1614/10/16

指纹

探究 'GPU-based fast signal processing for large amounts of snore sound data' 的科研主题。它们共同构成独一无二的指纹。

引用此