基于函数叠加法提升听障患者的听力效果  

Improving Hearing Effect of Hearing Impaired Patients Based on Function Superposition Method

作　　者：王咿卜 李建文[3] WANG Yibo;LI Jianwen(College of Mathematics and Computer Application,Shangluo University,Shangluo 726000,China;Engineering Research Center of Qinling Health Welfare Big Data,Universities of Shaanxi Province,Shangluo 726000,China;School of Electronic Information and Artificial Intelligence,Shaanxi University of Science&Technology,Xi’an 710021,China)

机构地区：[1]商洛学院,数学与计算机应用学院,陕西商洛726000 [2]秦岭康养大数据陕西省高校工程研究中心,陕西商洛726000 [3]陕西科技大学,电子信息与人工智能学院,陕西西安710021 [4]渭南师范学院

出　　处：《微型电脑应用》2025年第2期20-23,28,共5页Microcomputer Applications

基　　金：国家自然科学基金重点项目(60672001);商洛学院科学与技术研究基金项目(22SKY001)。

摘　　要：语音是影响听障患者身心健康的重要因素。由于听障患者在不同频率段会出现弱听现象,因此采用最小二乘法结合批量梯度下降法进行基频曲线拟合,结合语音的基频参数和共振峰参数,采用三角函数叠加法对接收到的语音进行再合成,研究了在特定频率段提高分贝值对听障患者提升语音效果的影响。结果表明,根据语音特征参数进行频谱曲线增强能够有针对性地弥补听障患者的听力缺陷。Speech is an important factor affecting the physical and mental health of the hearing impairedd patients.Because these patients may have weak hearing in different frequency range,the least square method and batch gradient descent method are used to fit the pitch frequency curve.Combining the pitch parameters and formant parameters of speech,the received speech is re-synthesized by using the triangle function superposition method.The effect of increasing the decibel value in a specific frequency range on improving the speech effect of patients with hearing impairment is studied.The results show that according to the characteristic parameters of speech,the enhanced spectrum curve can make up for the hearing defects of the hearing impaired.

关 键 词：听障患者 梯度下降 频谱曲线 语音合成 

分 类 号：TN912.33[电子电信—通信与信息系统]