A New Deep CNN Model for Environmental Sound Classification
Cognitive prediction in the complicated and active environments is of great importance role in artificial learning. Classification accuracy of sound events has a robust relation with the feature extraction. In this paper, deep features are used in the environmental sound classification (ESC) problem...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9052658/ |
id |
doaj-fca0fd7324c64591b15e7782529c2101 |
---|---|
record_format |
Article |
spelling |
doaj-fca0fd7324c64591b15e7782529c21012021-03-30T03:12:28ZengIEEEIEEE Access2169-35362020-01-018665296653710.1109/ACCESS.2020.29849039052658A New Deep CNN Model for Environmental Sound ClassificationFatih Demir0Daban Abdulsalam Abdullah1Abdulkadir Sengur2https://orcid.org/0000-0003-1614-2639Electrical and Electronics Engineering Department, Technolog Faculty, Firat University, Elazig, TurkeyResearch Center, Sulaimani Polytechnic University, Sulaimanyah, IraqElectrical and Electronics Engineering Department, Technolog Faculty, Firat University, Elazig, TurkeyCognitive prediction in the complicated and active environments is of great importance role in artificial learning. Classification accuracy of sound events has a robust relation with the feature extraction. In this paper, deep features are used in the environmental sound classification (ESC) problem. The deep features are extracted by using the fully connected layers of a newly developed Convolutional Neural Networks (CNN) model, which is trained in the end-to-end fashion with the spectrogram images. The feature vector is constituted with concatenating of the fully connected layers of the proposed CNN model. For testing the performance of the proposed method, the feature set is conveyed as input to the random subspaces K Nearest Neighbor (KNN) ensembles classifier. The experimental studies, which are carried out on the DCASE-2017 ASC and the UrbanSound8K datasets, show that the proposed CNN model achieves classification accuracies 96.23% and 86.70%, respectively.https://ieeexplore.ieee.org/document/9052658/Environmental sound classificationspectrogram imagesCNN modeldeep features |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Fatih Demir Daban Abdulsalam Abdullah Abdulkadir Sengur |
spellingShingle |
Fatih Demir Daban Abdulsalam Abdullah Abdulkadir Sengur A New Deep CNN Model for Environmental Sound Classification IEEE Access Environmental sound classification spectrogram images CNN model deep features |
author_facet |
Fatih Demir Daban Abdulsalam Abdullah Abdulkadir Sengur |
author_sort |
Fatih Demir |
title |
A New Deep CNN Model for Environmental Sound Classification |
title_short |
A New Deep CNN Model for Environmental Sound Classification |
title_full |
A New Deep CNN Model for Environmental Sound Classification |
title_fullStr |
A New Deep CNN Model for Environmental Sound Classification |
title_full_unstemmed |
A New Deep CNN Model for Environmental Sound Classification |
title_sort |
new deep cnn model for environmental sound classification |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Cognitive prediction in the complicated and active environments is of great importance role in artificial learning. Classification accuracy of sound events has a robust relation with the feature extraction. In this paper, deep features are used in the environmental sound classification (ESC) problem. The deep features are extracted by using the fully connected layers of a newly developed Convolutional Neural Networks (CNN) model, which is trained in the end-to-end fashion with the spectrogram images. The feature vector is constituted with concatenating of the fully connected layers of the proposed CNN model. For testing the performance of the proposed method, the feature set is conveyed as input to the random subspaces K Nearest Neighbor (KNN) ensembles classifier. The experimental studies, which are carried out on the DCASE-2017 ASC and the UrbanSound8K datasets, show that the proposed CNN model achieves classification accuracies 96.23% and 86.70%, respectively. |
topic |
Environmental sound classification spectrogram images CNN model deep features |
url |
https://ieeexplore.ieee.org/document/9052658/ |
work_keys_str_mv |
AT fatihdemir anewdeepcnnmodelforenvironmentalsoundclassification AT dabanabdulsalamabdullah anewdeepcnnmodelforenvironmentalsoundclassification AT abdulkadirsengur anewdeepcnnmodelforenvironmentalsoundclassification AT fatihdemir newdeepcnnmodelforenvironmentalsoundclassification AT dabanabdulsalamabdullah newdeepcnnmodelforenvironmentalsoundclassification AT abdulkadirsengur newdeepcnnmodelforenvironmentalsoundclassification |
_version_ |
1724183934744395776 |