|
|
【答案】应助回帖
★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★
感谢参与，应助指数 +1
hnzz001: 金币+20, ★★★★★最佳答案 2020-11-11 14:32:45
sunshan4379: LS-EPI+1, 感谢应助! 2020-11-16 20:26:21
Real time speech recognition algorithm on emb edded system based on continuous Markov model
作者:He, YQ (He, Yongqiang)[ 1,2 ] ; Dong, XG (Dong, Xiguang)[ 3 ]
MICROPROCESSORS AND MICROSYSTEMS
卷: 75
文献号: 103058
DOI: 10.1016/j.micpro.2020.103058
出版年: JUN 2020
文献类型:Article
查看期刊影响力
摘要
Real time speech recognition technology, as a key cross technology in the field of artificial intelligence in recent years, has been widely used in the fields of intelligent voice toys, industrial control and intelligent rehabilitation. Because the real-time speech recognition technology based on embedded technology has obvious advantages in the volume, power consumption and research and development cost of the system, it has become a hot carrier to achieve efficient speech recognition technology. In order to realize a simple and practical real-time speech recognition system based on embedded system, this paper designs a basic framework of machine learning based on Markov random field theory combined with machine learning theory, and studies the algorithm of real-time speech vocabulary matching recognition based on this framework. In detail, the algorithm proposed in this paper will process the speech signal from the aspects of preprocessing, signal detection, feature extraction and quantization. Finally, this paper will build a realtime speech recognition system based on DSP processor. The experimental results show that the real-time speech recognition algorithm proposed in this paper can improve the real-time recognition speed of the system. The corresponding speed changes from about 12 s to about 200 ms, and the corresponding realtime accuracy rate increases to about 95%. (C) 2020 Elsevier B.V. All rights reserved.
关键词
作者关键词:Real-time speech recognition system; Markov model; Embedded system; real-time speech vocabulary matching; algorithm; DSP signal processor
KeyWords Plus:INFORMATION
作者信息
通讯作者地址:
Henan University of Engineering Henan Univ Engn, Coll Comp, Zhengzhou, Peoples R China.
Henan IoT Engn Res Ctr Smart Bldg, Zhengzhou, Peoples R China.
通讯作者地址: He, YQ (通讯作者)
显示更多 Henan Univ Engn, Coll Comp, Zhengzhou, Peoples R China.
通讯作者地址: He, YQ (通讯作者)
Henan IoT Engn Res Ctr Smart Bldg, Zhengzhou, Peoples R China.
地址:
显示更多 [ 1 ] Henan Univ Engn, Coll Comp, Zhengzhou, Peoples R China
[ 2 ] Henan IoT Engn Res Ctr Smart Bldg, Zhengzhou, Peoples R China
显示更多 [ 3 ] Henan Univ Engn, Coll Sci, Zhengzhou, Peoples R China
电子邮件地址:yqhe@haue.edu.cn
出版商
ELSEVIER, RADARWEG 29, 1043 NX AMSTERDAM, NETHERLANDS
期刊信息
Impact Factor (影响因子): Journal Citation Reports
类别 / 分类
研究方向:Computer Science; Engineering
Web of Science 类别:Computer Science, Hardware & Architecture; Computer Science, Theory & Methods; Engineering, Electrical & Electronic
文献信息
语言:English
入藏号: WOS:000535859600031
ISSN: 0141-9331
eISSN: 1872-9436
其他信息
IDS 号: LR7FU
Web of Science 核心合集中的 "引用的参考文献": 21
Web of Science 核心合集中的 "被引频次": 0 |
|
回复此楼