朱知萌,郭育,王冠,章佳荣.水下蛙人呼吸声Mel倒谱特征的实验研究[J].声学技术,2017,36(3):286~292 |
水下蛙人呼吸声Mel倒谱特征的实验研究 |
Experimental research on Mel cepstrum feature of the underwater diver breathing-signal |
投稿时间:2016-09-21 修订日期:2016-12-09 |
DOI:10.16300/j.cnki.1000-3630.2017.03.016 |
中文关键词: 被动声呐 水下小目标 Mel频率倒谱系数 特征匹配 |
英文关键词: passive sonar underwater small target Mel Frequency Cepstrum Coefficient (MFCC) feature matching |
基金项目: |
|
摘要点击次数: 1413 |
全文下载次数: 1173 |
中文摘要: |
为提高水下蛙人呼吸声识别的准确度,提出一种基于Mel频率倒谱系数(Mel Frequency Cepstrum Coefficient,MFCC)的蛙人呼吸声信号特征匹配方法。计算呼吸声信号之间、信号与环境噪声及舰船辐射噪声的MFCC夹角和MFCC距离并进行匹配比较,以进行分类识别。某湖试验数据的处理结果表明:蛙人呼吸声与舰船辐射噪声及环境噪声的MFCC参数有着明显的差异,能够对蛙人呼吸声信号与干扰噪声进行区分,证明了基于MFCC特征算法的有效性,对发展港口、码头等近海海域附近的水下蛙人探测声呐和预警系统具有实际意义。 |
英文摘要: |
In order to improve the accuracy of the diver breathing-signal recognition,this paper presents a method of matching underwater diver breathing-signal based on MFCC.Breathing-signal of the underwater diver is obtained during the trial in Songhua River,Jilin province,and the MFCC angle and MFCC distance between breathing-signal,ship-radiated noise and ambient noise are calculated and matched.The results show that there is an obvious difference of the MFCC parameter between diver breathing-signal and noise,the validity of the MFCC based feature algorithm is verified,which has a reference value for the development of underwater diver sonar and early warning system in offshore areas. |
查看全文
查看/发表评论 下载PDF阅读器 |
关闭 |