Acoustic Scene Classification via Classifiers Voting

作     者：Shawn Sudheer Sagar 

作者单位：华南理工大学 

学位级别：硕士

导师姓名：李艳雄

授予年度：2020年

学科分类：0711[理学-系统科学] 07[理学] 

摘      要：Acoustic Scene Classification（ASC）is the recognition and categorization of audio data that identifies the environment which it has been *** is quite a challenging application of machine listening due to the noisy nature of the audio *** analyze several state-of-the-art models for ASC on two different *** datasets belong to the IEEE challenge on the Detection and Classification of Acoustic Scenes and Events（DCASE）2017 and *** two datasets are publicly available for research purpose,and consist of 10 and 15 classes of acoustic scenes *** total,57 hours of stereo recordings are available which includes common indoor and outdoor environmental scenes,such as beach,city center,library,forest path train,car,*** propose a method of ASC via fusing the voting of deep neural *** the proposed method,two different acoustic features are first extracted from each audio recording *** cepstral coefficients（MFCC）and Logarithmic filter-bank（LFB）.These features are then fed into three different classifiers（deep neural networks）: Visual Geometry Group（VGG）,Residual Network（Res Net）and Long Short-Term Memory（LSTM）.The motivation for choosing these variety of neural networks is that they have complementary advantages for *** training each network and acquiring the results,fusion of classifiers voting is used to determine a final *** fusion of all the results through voting technique is one of the methods under ensemble *** final Classification Accuracies（CA）that are obtained after the fusion of the classifiers are 73.27% and 76.99% on DCASE 2017 and 2019 datasets *** proposed fusion of classifiers voting obtains the CA improvements by 12.71% and 13.79% on DCASE 2017 and 2019 datasets respectively,compared to the individual baseline classifiers.