{ "article_id": 1426, "public_id": "9bea1e42-5629-483c-990c-77d61059758f", "internal_identifier": null, "source_identifier": "88:11", "status": "published", "type": "research_article", "title": "Videolardaki Çevresel Sesleri Tanımak İçin Derin Öğrenme Tabanlı Bir Model Geliştirme", "title_secondary": null, "abstract": "Günümüzde çevremizdeki çeşitli seslerin ayrıştırılarak ortam tanıma işlemi popülerlik kazanmıştır. Videolarda arka plandaki çeşitli sesler, makine öğrenmesi ve derin öğrenme teknikleriyle oldukça yüksek başarıyla sınıflandırılabilmektedir. Böylece anlamsal olarak zenginleştirilmiş video sahneleri betimlenebilmektedir. Bu çalışma, çevresel seslerin tanımlanması için uygun bir derin öğrenme sinir ağı modelinin geliştirilmesi sürecini içermektedir. Geliştirilen modelin eğitilmesinde çeşitli veriler içeren veri kümesinden on tane temel kategori seçilerek modelin tahminleme gücü deneylerde sınanmıştır. Elde bulunan sınırlı veriden öncelikle spektrogramlar elde edilip daha sonra bu spektrogramlar veri arttırma teknikleri kullanılarak zenginleştirilmiştir. Ayrıca, modelin eğitilmesinde üç farklı tasarımsal yaklaşım ile kaynak kodlar yazılmıştır. Bu kodlar Evrişimsel Sinir Ağları, Uzun Kısa Süreli Bellek, Kapılı Tekrarlayan Birim gibi derin öğrenme ağ modeli tabanlı yöntemler kullanılarak oluşturulmuştur. Tasarlanan yedi farklı sinir ağı modeli deneylerde eğitilmiş ve testler ile başarımı kanıtlanmıştır. Oluşturulan modellerin en yüksek başarıma sahip olanı ile yaklaşık %87 oranında doğruluk oranı elde edilmiştir. Elde edilen deneysel sonuçlara ve bilimsel değerlendirmeye çalışmamızda yer verilmektedir.", "language": "tr", "english_title": "Development of a Deep Learning Based Model for Recognizing the Environmental Sounds in Videos", "english_abstract": "Nowadays, decomposition of various environmental sounds for environment recognition has gained popularity. Various background sounds in videos could be classified with high success with deep learning and machine learning techniques. In this way, semantically enriched video scenes can be depicted. This work contains the process of developing a convenient deep learning neural network model for environmental sounds recognition. In training the developed model, ten main categories have been chosen from a dataset that has various data to test the model's prediction power by experiment. From the limited data available, first, spectrograms have been produced and then, these spectrograms have been enriched by the help of data augmentation techniques. In this way, attribute diversity that was gained from data has been increased. Also, with three different design approaches for training the model, source codes have been written. These codes have been created by using deep learning network model-based methods such as Convolutional Neural Networks, Long Short Term Memory, Gated Recurrent Unit. Seven different designed neural network models have been trained by experiments and achievement has been proved by tests. With the highest accuracy obtained from one of the generated models, approximately %87 of accuracy has been obtained. This work contains obtained experimental results and scientific evaluation.", "doi": "10.36287/setsci.5.1.011", "doi_url": "https://doi.org/10.36287/setsci.5.1.011", "resource_url": "https://www.set-science.com/a/9bea1e42-5629-483c-990c-77d61059758f", "pdf_url": "https://www.set-science.com/a/9bea1e42-5629-483c-990c-77d61059758f/pdf", "og_image": "https://www.set-science.com/assets/img/og-card-v2.png", "authors": [ { "public_id": "ce6ca3ee-a5cb-492b-bcac-cd001e6cc6ac", "given": "Bedirhan", "family": "Karakaya", "full": "Bedirhan Karakaya", "literal": null, "orcid": null, "orcid_url": null, "email": "bedirhankrkya@gmail.com", "corresponding": true, "sequence": "first", "affiliations": [ { "name": "Çanakkale Onsekiz Mart Üniversitesi, Bilgisayar Mühendisliği Bölümü", "department": null, "country": null, "country_code": null, "ror": null, "ror_url": null } ] }, { "public_id": "9c9a1390-52d9-4973-b1bf-1797c15c5ccd", "given": "Emre Beray", "family": "Boztepe", "full": "Emre Beray Boztepe", "literal": null, "orcid": null, "orcid_url": null, "email": "berayboztepe@outlook.com", "corresponding": false, "sequence": "additional", "affiliations": [ { "name": "Çanakkale Onsekiz Mart Üniversitesi, Bilgisayar Mühendisliği Bölümü", "department": null, "country": null, "country_code": null, "ror": null, "ror_url": null } ] }, { "public_id": "35da26c1-1bda-430c-b320-b9bddb318cec", "given": "Bahadır", "family": "Karasulu", "full": "Bahadır Karasulu", "literal": null, "orcid": null, "orcid_url": null, "email": "noname@noname.eu", "corresponding": false, "sequence": "additional", "affiliations": [ { "name": "Çanakkale Onsekiz Mart Üniversitesi, Bilgisayar Mühendisliği Bölümü", "department": null, "country": null, "country_code": null, "ror": null, "ror_url": null } ] } ], "keywords": [ "Evrişimsel Sinir Ağları", "Tekrarlayan Sinir Ağları", "Çevresel Ses Tanıma" ], "translations": [ { "language": "en", "title": "Development of a Deep Learning Based Model for Recognizing the Environmental Sounds in Videos", "abstract": "Nowadays, decomposition of various environmental sounds for environment recognition has gained popularity. Various background sounds in videos could be classified with high success with deep learning and machine learning techniques. In this way, semantically enriched video scenes can be depicted. This work contains the process of developing a convenient deep learning neural network model for environmental sounds recognition. In training the developed model, ten main categories have been chosen from a dataset that has various data to test the model's prediction power by experiment. From the limited data available, first, spectrograms have been produced and then, these spectrograms have been enriched by the help of data augmentation techniques. In this way, attribute diversity that was gained from data has been increased. Also, with three different design approaches for training the model, source codes have been written. These codes have been created by using deep learning network model-based methods such as Convolutional Neural Networks, Long Short Term Memory, Gated Recurrent Unit. Seven different designed neural network models have been trained by experiments and achievement has been proved by tests. With the highest accuracy obtained from one of the generated models, approximately %87 of accuracy has been obtained. This work contains obtained experimental results and scientific evaluation.", "keywords": [ "Convolutional Neural Networks", "Recurrent Neural Networks", "Environmental Sound Recognition" ] } ], "subjects": [], "subject_names": [], "published_date": "2022-06-01", "published_year": "2022", "received_date": null, "accepted_date": null, "volume": "13", "issue": null, "page_first": "53", "page_last": "58", "article_number": null, "conference": { "short_name": "ISAS2022", "full_title": "5th International Symposium on Innovative Approaches in Smart Technologies", "name": "5th International Symposium on Innovative Approaches in Smart Technologies", "acronym": "ISAS2022", "location": "Online, Türkiye", "start_date": "2022-05-28", "end_date": null, "public_id": "23436f3c-bde1-4f59-b3be-a8ccc770539f" }, "proceedings": { "title": "Proceeding of the 5th International Symposium on Innovative Approaches in Smart Technologies", "series_title": "SETSCI Conference Proceedings", "publisher": "SET Technology", "isbn": null, "eisbn": "978-625-95366-9-9", "issn": null, "eissn": "2687-5527", "doi": null, "doi_prefix": "10.36287", "slug": "setsci-volume-13-2022-legacy-88", "public_id": "04c79b09-4b3a-4deb-84ea-b349d80e3e9e", "url": "https://www.set-science.com/p/setsci-volume-13-2022-legacy-88" }, "license": { "name": "CC BY 4.0", "url": "https://creativecommons.org/licenses/by/4.0/", "code": "CC-BY-4.0", "open_access": true }, "copyright": { "holder": "SET Technology", "year": "2022" }, "funding_statement": null, "funders": [], "references": [ { "order": 1, "raw": "B., Karasulu. “Çoklu Ortam Sistemleri İçin Siber Güvenlik Kapsamında Derin Öğrenme Kullanarak Ses Sahne ve Olaylarının Tespiti” ACTA INFOLOGICA, 3(2):60-82, 2019. doi: 10.26650/acin.590690", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 2, "raw": "K. J. Piczak, “Environmental sound classification with convolutional neural networks”, 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP), Boston, MA, USA pp. 1-6. 2015. doi: 10.1109/MLSP.2015.7324337", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 3, "raw": "L., Shaobo, Y., Yao, J., Hu, G., Liu, X. Yao, and J., Hu. “An ensemble stacked convolutional neural network model for environmental event sound recognition”, Applied Sciences, vol. 8, no. 7 (2018): 1152. 2018. doi: 10.3390/app8071152", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 4, "raw": "A., Khamparia, D., Gupta, N.G., Nguyen, A., Khanna, B., Pandey and P., Tiwari, “Sound Classification Using Convolutional Neural Network and Tensor Deep Stacking Network”, IEEE Access, vol. 7, pp. 7717-7727, 2019. doi: 10.1109/ACCESS.2018.2888882", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 5, "raw": "A. Krizhevsky, I. Sutskever, G.E. Hinton. “ImageNet Classification with Deep Convolutional Neural Networks”, Advances in Neural Information Processing Systems, Editörler: F. Pereira and C.J. Burges and L. Bottou and K.Q. Weinberger, Curran Associates, Inc., Vol. 25, 2012. [Online]: https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 6, "raw": "MFCC (Mel-frequency cepstral coefficient) dokümantasyonu, 2022. https://librosa.org/doc/main/generated/librosa.feature.mfcc.html", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 7, "raw": "Chroma ses özniteliği dokümantasyonu, 2022. [Online]. https://librosa.org/doc/main/generated/librosa.feature.chroma_stft.html", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 8, "raw": "B. McFee, C. Raffel, D. Liang, D.P. Ellis, M. McVicar, E. Battenberg and O. Nieto. \"librosa: Audio and Music Signal Analysis in Python\", In Proceedings of the 14th Python in Science Conference, volume 8, 2015. doi: 10.25080/Majora-7b98e3ed-003", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 9, "raw": "N., Marwan, M., Thiel, N.R. and Nowaczyk. “Cross Recurrence Plot Based Synchronization of Time Series”. In: Nonlinear Processes in Geophysics 9 (2002), 325-331. 2002.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 10, "raw": "ESC-50 veri kümesi, 2022. [Online]. https://github.com/karolpiczak/ESC-50", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 11, "raw": "Çoklu Maskeleme işlemi dokümantasyonu, 2022. [Online]. https://www.tensorflow.org/io/tutorials/audio", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 12, "raw": "Keras Kütüphanesi dokümantasyonu, 2022. [Online]. https://keras.io", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 13, "raw": "ResNet50 sinir ağı modeli dokümantasyonu, 2022. [Online]. https://keras.io/api/applications/resnet/#resnet50-function", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 14, "raw": "MobileNetV2 sinir ağı modeli dokümantasyonu, 2022. [Online]. https://keras.io/api/applications/mobilenet/#mobilenetv2-function", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 15, "raw": "VGG16 ve VGG19 sinir ağı modelleri dokümantasyonu, 2022. [Online]. https://keras.io/api/applications/vgg/#vgg16-function", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 16, "raw": "Tensorflow kütüphanesi dokümantasyonu, 2022. [Online]. https://www.tensorflow.org/api_docs", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 17, "raw": "Y., Aytar, C., Vondrick, A., Torralba. “SoundNet: Learning Sound Representations from Unlabeled Video “. arXiv preprint arXiv : 1610.09001v1 [cs.CV] 2016", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 18, "raw": "SoundNet kütüphanesinin Github İnternet Erişim Adresi, 2022, [Online]. https://github.com/JarbasAl/soundnet", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 19, "raw": "Altyapıda kullanılan çeşitli kütüphanelerin dokümantasyonları, 2022. [Online]. https://pypi.org", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 20, "raw": "DCASE (Detection and Classification of Acoustic Scenes and Events) veri kümesi, 2022. [Online]. http://dcase.community", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 21, "raw": "Kesit alınan bilgisayar oyununun oynanış videosu, 2022. [Online]. https://www.youtube.com/watch?v=d74REG039Dk", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 22, "raw": "D.S., Park, W., Chan., Y., Zhang, C.-C., Chiu, B., Zoph, E.D., Cubuk and Q.V., Le. “SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition”. arXiv preprint: arXiv:1904.08779v3 [eess.AS]. 2019", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 23, "raw": "J. You and J. Korhonen. \"Attention Boosted Deep Networks For Video Classification\", 2020 IEEE International Conference on Image Processing (ICIP), 2020, pp. 1761-1765. doi: 10.1109/ICIP40778.2020.9190996", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 24, "raw": "Z., Zhang, S., Xu, S., Zhang, T., Qiao and S., Cao. \"Learning Attentive Representations for Environmental Sound Classification\", IEEE Access, vol. 7, pp. 130327-130339, 2019. doi: 10.1109/ACCESS.2019.2939495", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 25, "raw": "B., Karasulu. “Kısıtlanmış Boltzmann makinesi ve farklı sınıflandırıcılarla oluşturulan sınıflandırma iş hatlarının başarımının değerlendirilmesi”, Bilişim Teknolojileri Dergisi, 11(3), 223-233, 2018. doi: 10.17671/gazibtd.370281", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null } ], "statements": { "acknowledgements": null, "conflict_of_interest": null, "data_availability": null, "ai_disclosure": null }, "credit": [], "history": { "published": "2022-06-01" } }