强环境噪声下船用耳罩语音增强仿真与验证  被引量:1

Simulation and Verification on Speech Enhancement of Marine Earmuffs under Strong Environmental Noise

在线阅读下载全文

作  者:杨理华 张翔鹏 刘丽滨 艾夏禹 杨军[2,3] YANG Li-hua;ZHANG Xiang-peng;LIU Li-bin;AI Xia-yu;YANG Jun(Navy Submarine Academy,Qingdao Shandong 266199,China;Key Laboratory of Noise and Vibration Research,Institute of Acoustics,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区:[1]海军潜艇学院,山东青岛266199 [2]中国科学院噪声与振动实验室(声学研究所),北京100190 [3]中国科学院大学,北京100049

出  处:《船海工程》2023年第1期87-92,共6页Ship & Ocean Engineering

基  金:国家自然科学基金(51909267);山东省自然科学基金(ZR2019QEE031)。

摘  要:针对某船用通信耳罩在强环境噪声条件下,语音通信受严重影响甚至无法正常工作的问题,构建某船用语音通信系统架构和模型,提出一种联级型语音增强算法,分析系统参数对控制效果的影响,并搭建高性能噪声控制验证平台对所述算法进行验证。结果表明,所提出的算法的能有效降低麦克风语音通讯时强环境噪声干扰,提升语音通信信噪比,显著消除粉色噪声和线谱噪声的不利影响,降低人员移动时参考信号不稳定性对控制效果的影响,可为通讯系统耳罩改进提供技术参考。Aiming at the problem that the voice communication of a marine communication earmuff is seriously affected,or even cannot work normally under the condition of strong environmental noise,the architecture and model of a marine voice communication system were constructed,and a cascaded voice enhancement algorithm was proposed to analyze the influence of the system parameters upon the control effect.A high-performance noise control verification platform was built to verify the algorithm.The results showed that the proposed cascaded speech enhancement algorithm can effectively reduce the strong environmental noise interference during microphone speech communication,and improve the signal-to-noise ratio of speech communication,significantly eliminate the adverse effects of pink noise and line spectrum noise,and reduce the influence of reference signal instability on the control effect when the crew is moving.All of which can provide a technical reference for the improvement of the earmuffs of the later communication system.

关 键 词:船用 耳罩 麦克风 语音增强 

分 类 号:U667.7[交通运输工程—船舶及航道工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象