Personalized HRTF Prediction Based on Light GBM Using Anthropometric Data

作     者：Yinliang Qiu Jing Wang Zhiyu Li Yinliang Qiu;Jing Wang;Zhiyu Li

作者机构：School of Information and ElectronicsBeijing Institute of TechnologyBeijing 100876China 

出 版 物：《China Communications》 (中国通信（英文版）)

年 卷 期：2023年第20卷第6期

页      面：166-177页

核心收录：

学科分类：0810[工学-信息与通信工程] 070207[理学-光学] 07[理学] 08[工学] 0803[工学-光学工程] 0702[理学-物理学] 

基　　金：supported by the cooperation between BIT and Ericsson partially supported by the National Natural Science Foundation of China under Grants No.62071039 

主　　题：personalized HRTF anthropometric data LightGBM over-fitting 

摘      要：This paper proposes a personalized headrelated transfer function(HRTF)prediction method based on Light GBM using anthropometric *** the overfitting problems of the current training-based prediction methods,we use Light GBM and a specific network structure to prevent over-fitting and enhance the prediction *** decomposing and combining the data to be predicted,we set up 90 Light GBM models to separately predict the 90instants of HRTF in log *** the same time,the method of 10-fold cross-validation is used to score the accuracy of the *** models with scores below 80 points,Bayesian optimization is used to adjust model hyperparameters to obtain a better model *** results obtained by Light GBM are evaluated with spectral distortion(SD)which can show the fitting error between the prediction and the original *** mean SD values of both ears on the whole test set are 2.32 d B and 2.28 d B *** with the non-linear regression method and the latest method,SD value of Light GBM-based method relatively decreases by 83.8%and 48.5%.