Deep Learning-based Environmental Sound Classification Using Feature Fusion and Data Enhancement

作     者：Rashid Jahangir Muhammad Asif Nauman Roobaea Alroobaea Jasem Almotiri Muhammad Mohsin Malik Sabah M.Alzahrani 

作者机构：Department of Computer ScienceCOMSATS University IslamabadVehari CampusPakistan Department of Computer ScienceUniversity of Engineering and Technology LahorePakistan Department of Computer ScienceCollege of Computers and Information TechnologyTaif UniversityTaif21974Saudi Arabia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2023年第74卷第1期

页      面：1069-1091页

核心收录：

学科分类：12[管理学] 080801[工学-电机与电器] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0808[工学-电气工程] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the Taif University Researchers Supporting Project number(TURSP-2020/36) Taif University Taif Saudi Arabia 

主　　题：Environmental sound classification convolutional neural network deep learning transformer data augmentation 

摘      要：Environmental sound classification(ESC)involves the process of distinguishing an audio stream associated with numerous environmental *** common aspects such as the framework difference,overlapping of different sound events,and the presence of various sound sources during recording make the ESC task much more complicated and *** research is to propose a deep learning model to improve the recognition rate of environmental sounds and reduce the model training time under limited computation *** this research,the performance of transformer and convolutional neural networks(CNN)are *** audio features,chromagram,Mel-spectrogram,tonnetz,Mel-Frequency Cepstral Coefficients(MFCCs),delta MFCCs,delta-delta MFCCs and spectral contrast,are extracted fromtheUrbanSound8K,ESC-50,and ESC-10,***,this research also employed three data enhancement methods,namely,white noise,pitch tuning,and time stretch to reduce the risk of overfitting issue due to the limited audio *** evaluation of various experiments demonstrates that the best performance was achieved by the proposed transformer model using seven audio features on enhanced *** UrbanSound8K,ESC-50,and ESC-10,the highest attained accuracies are 0.98,0.94,and 0.97 *** experimental results reveal that the proposed technique can achieve the best performance for ESC problems.