Animal Sound Classification Using A Convolutional Neural Network

Emre Sasmaz; F. Boray Tek

doi:10.1109/UBMK.2018.8566449

Animal Sound Classification Using A Convolutional Neural Network

Emre Sasmaz
, F. Boray Tek

Isik University

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

43 Atıf (Scopus)

Özet

In this paper, we investigate the problem of animal sound classification using deep learning and propose a system based on convolutional neural network architecture. As the input to the network, sound files were preprocessed to extract Mel Frequency Cepstral Coefficients (MFCC) using LibROSA library. To train and test the system we have collected 875 animal sound samples from an online sound source site for 10 different animal types. We report classification confusion matrices and the results obtained by different gradient descent optimizers. The best accuracy of 75% was obtained by Nesterov-accelerated Adaptive Moment Estimation (Nadam).

Orijinal dil	İngilizce
Ana bilgisayar yayını başlığı	UBMK 2018 - 3rd International Conference on Computer Science and Engineering
Yayınlayan	Institute of Electrical and Electronics Engineers Inc.
Sayfalar	625-629
Sayfa sayısı	5
ISBN (Elektronik)	9781538678930
DOI'lar	https://doi.org/10.1109/UBMK.2018.8566449
Yayın durumu	Yayınlandı - 6 Ara 2018
Harici olarak yayınlandı	Evet
Etkinlik	3rd International Conference on Computer Science and Engineering, UBMK 2018 - Sarajevo, Bosnia and Herzegovina Süre: 20 Eyl 2018 → 23 Eyl 2018

Yayın serisi

Adı	UBMK 2018 - 3rd International Conference on Computer Science and Engineering

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	3rd International Conference on Computer Science and Engineering, UBMK 2018
Ülke/Bölge	Bosnia and Herzegovina
Şehir	Sarajevo
Periyot	20/09/18 → 23/09/18

Bibliyografik not

Publisher Copyright:
© 2018 IEEE.

Belgeye Erişim

10.1109/UBMK.2018.8566449

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

Sasmaz, E., & Tek, F. B. (2018). Animal Sound Classification Using A Convolutional Neural Network. In UBMK 2018 - 3rd International Conference on Computer Science and Engineering (pp. 625-629). Makale 8566449 (UBMK 2018 - 3rd International Conference on Computer Science and Engineering). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/UBMK.2018.8566449

@inproceedings{f855da3cf08243059c49d07cca03ab1a,

title = "Animal Sound Classification Using A Convolutional Neural Network",

abstract = "In this paper, we investigate the problem of animal sound classification using deep learning and propose a system based on convolutional neural network architecture. As the input to the network, sound files were preprocessed to extract Mel Frequency Cepstral Coefficients (MFCC) using LibROSA library. To train and test the system we have collected 875 animal sound samples from an online sound source site for 10 different animal types. We report classification confusion matrices and the results obtained by different gradient descent optimizers. The best accuracy of 75\% was obtained by Nesterov-accelerated Adaptive Moment Estimation (Nadam).",

keywords = "Animal sound classification, Confusion Matrix (CF), Convolution Neural Network (CNN), Mel Frequency Cepstral Coefficient (MFCC)",

author = "Emre Sasmaz and Tek, \{F. Boray\}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 3rd International Conference on Computer Science and Engineering, UBMK 2018 ; Conference date: 20-09-2018 Through 23-09-2018",

year = "2018",

month = dec,

day = "6",

doi = "10.1109/UBMK.2018.8566449",

language = "English",

series = "UBMK 2018 - 3rd International Conference on Computer Science and Engineering",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "625--629",

booktitle = "UBMK 2018 - 3rd International Conference on Computer Science and Engineering",

address = "United States",

}

Sasmaz, E & Tek, FB 2018, Animal Sound Classification Using A Convolutional Neural Network. in UBMK 2018 - 3rd International Conference on Computer Science and Engineering., 8566449, UBMK 2018 - 3rd International Conference on Computer Science and Engineering, Institute of Electrical and Electronics Engineers Inc., pp. 625-629, 3rd International Conference on Computer Science and Engineering, UBMK 2018, Sarajevo, Bosnia and Herzegovina, 20/09/18. https://doi.org/10.1109/UBMK.2018.8566449

Animal Sound Classification Using A Convolutional Neural Network. / Sasmaz, Emre; Tek, F. Boray.
UBMK 2018 - 3rd International Conference on Computer Science and Engineering. Institute of Electrical and Electronics Engineers Inc., 2018. p. 625-629 8566449 (UBMK 2018 - 3rd International Conference on Computer Science and Engineering).

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

TY - GEN

T1 - Animal Sound Classification Using A Convolutional Neural Network

AU - Sasmaz, Emre

AU - Tek, F. Boray

PY - 2018/12/6

Y1 - 2018/12/6

N2 - In this paper, we investigate the problem of animal sound classification using deep learning and propose a system based on convolutional neural network architecture. As the input to the network, sound files were preprocessed to extract Mel Frequency Cepstral Coefficients (MFCC) using LibROSA library. To train and test the system we have collected 875 animal sound samples from an online sound source site for 10 different animal types. We report classification confusion matrices and the results obtained by different gradient descent optimizers. The best accuracy of 75% was obtained by Nesterov-accelerated Adaptive Moment Estimation (Nadam).

AB - In this paper, we investigate the problem of animal sound classification using deep learning and propose a system based on convolutional neural network architecture. As the input to the network, sound files were preprocessed to extract Mel Frequency Cepstral Coefficients (MFCC) using LibROSA library. To train and test the system we have collected 875 animal sound samples from an online sound source site for 10 different animal types. We report classification confusion matrices and the results obtained by different gradient descent optimizers. The best accuracy of 75% was obtained by Nesterov-accelerated Adaptive Moment Estimation (Nadam).

KW - Animal sound classification

KW - Confusion Matrix (CF)

KW - Convolution Neural Network (CNN)

KW - Mel Frequency Cepstral Coefficient (MFCC)

UR - https://www.scopus.com/pages/publications/85060595306

U2 - 10.1109/UBMK.2018.8566449

DO - 10.1109/UBMK.2018.8566449

M3 - Conference contribution

AN - SCOPUS:85060595306

T3 - UBMK 2018 - 3rd International Conference on Computer Science and Engineering

SP - 625

EP - 629

BT - UBMK 2018 - 3rd International Conference on Computer Science and Engineering

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd International Conference on Computer Science and Engineering, UBMK 2018

Y2 - 20 September 2018 through 23 September 2018

ER -

Animal Sound Classification Using A Convolutional Neural Network

Özet

Yayın serisi

???event.eventtypes.event.conference???

Bibliyografik not

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap