基于AI的噪声环境下远距离高清音频采集研究  

Research on AI⁃based remote HD audio acquisition in noisy environment

作　　者：黄丽娜[1] HUANG Lina(Jiangxi University of Science and Technology,Ganzhou 341000,China)

机构地区：[1]江西理工大学,江西赣州341000

出　　处：《现代电子技术》2025年第4期130-134,共5页Modern Electronics Technique

摘　　要：为提升远距离采集音频信号的强度,深度滤除音频信号噪声以提取有用音频部分,提出一种基于AI的噪声环境下远距离高清音频采集方法。构建远距离高清音频采集结构,分别通过模拟增益和数字增益技术进行音频信号增益处理,以提升音频信号强度。依据短时傅里叶变换提取音频增益信号频域特征,输入到长短期记忆网络中,实现音频信号深度噪声去除,得到高清音频频域信息;再通过短时傅里叶逆变换处理该信号,实现音频信号重构,最终达到噪声环境下远距离高清音频采集的目的。实验验证结果表明:依据音频信号增益能够有效提升采集音频信号的强度,并避免信号受距离、噪声影响而逐渐衰减,继而有效滤除音频信号噪声数据,提取其中有用的音频信号,确保音频信号高清度;且最终采集音频信号信噪比均高于18 dB,可懂度均高于97%,有效验证了所提方法的有效性和准确性。In order to enhance the strength of long-distance audio signal acquisition and deeply filter out audio signal noise to extract useful audio parts,a method of AI-based remote high-definition(HD)audio acquisition in noisy environments is proposed.The remote HD audio acquisition structure is constructed,and the analog gain and digital gain techniques are used to conduct the audio signal gain processing,so as to improve the strength of audio signal.The frequency domain features of audio gain signals are extracted based on short-time Fourier transform,which are inputted into long short-term memory network to realize the deep noise removal of audio signals and obtain HD audio frequency domain information.The signal is processed by means of short-time Fourier inverse transform,to realize the audio signal reconstruction,ultimately achieving the goal of remote HD audio acquisition in noisy environments.The experimental verification results show that the gain of the audio signal can effectively enhance the strength of the collected audio signal,and avoid the gradual attenuation of the signal due to distance and noise,effectively filtering out the noise data of the audio signal,extracting useful music signals,and ensuring HD of the audio signal.The final collected audio signal signal-to-noise ratio was higher than 18 dB,and the comprehensibility was higher than 97%,effectively verifying the effectiveness and accuracy of the proposed method.

关 键 词：高清音频采集 AI 噪声环境 信号强度 远距离 长短期记忆网络 短时傅里叶变换 

分 类 号：TN912.3-34[电子电信—通信与信息系统] TP399[电子电信—信息与通信工程]