Convolutional Neural Networks and Transfer Learning Applied to Automatic Composition of Descriptive Music

被引:0
|
作者
Martin-Gomez, Lucia [1 ]
Perez-Marcos, Javier [1 ]
Navarro-Caceres, Maria [1 ]
Rodriguez-Gonzalez, Sara [1 ]
机构
[1] Univ Salamanca, BISITE Digital Innovat Hub, Edificio Multiusos I D I, Salamanca 37007, Spain
关键词
Descriptive music; Automatic composition; Image; Video; Transfer learning; Convolutional neural networks;
D O I
10.1007/978-3-319-99608-0_31
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Visual and musical arts has been strongly interconnected throughout history. The aim of this work is to compose music on the basis of the visual characteristics of a video. For this purpose, descriptive music is used as a link between image and sound and a video fragment of film Fantasia is deeply analyzed. Specially, convolutional neural networks in combination with transfer learning are applied in the process of extracting image descriptors. In order to establish a relationship between the visual and musical information, Naive Bayes, Support Vector Machine and Random Forest classifiers are applied. The obtained model is subsequently employed to compose descriptive music from a new video. The results of this proposal are compared with those of an antecedent work in order to evaluate the performance of the classifiers and the quality of the descriptive musical composition.
引用
收藏
页码:275 / 282
页数:8
相关论文
共 50 条
  • [41] Using Winning Lottery Tickets in Transfer Learning for Convolutional Neural Networks
    Van Soelen, Ryan
    Sheppard, John W.
    2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [42] Transfer Learning with Convolutional Neural Networks for Classification of Abdominal Ultrasound Images
    Cheng, Phillip M.
    Malhi, Harshawn S.
    JOURNAL OF DIGITAL IMAGING, 2017, 30 (02) : 234 - 243
  • [43] Compact Convolutional Neural Networks for Pterygium Classification using Transfer Learning
    Abdani, Siti Raihanah
    Zulkifley, Mohd Asyraf
    Hussain, Aini
    PROCEEDINGS OF THE 2019 IEEE INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING APPLICATIONS (IEEE ICSIPA 2019), 2019, : 140 - 143
  • [44] Epileptic Seizure Recognition Using Convolutional Neural Networks and Transfer Learning
    Cao Y.
    Gao C.
    Yu H.
    Wang J.
    Tianjin Daxue Xuebao (Ziran Kexue yu Gongcheng Jishu Ban)/Journal of Tianjin University Science and Technology, 2021, 54 (10): : 1094 - 1100
  • [45] Operational state detection in hydrocyclones with convolutional neural networks and transfer learning
    Giglia, K. C.
    Aldrich, C.
    MINERALS ENGINEERING, 2020, 149
  • [46] The Impact of Dataset Complexity on Transfer Learning over Convolutional Neural Networks
    Wanderley, Miguel D. de S.
    de A. e Bueno, Leonardo
    Zanchettin, Cleber
    Oliveira, Adriano L. I.
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, PT II, 2017, 10614 : 582 - 589
  • [47] Multisource Transfer Learning With Convolutional Neural Networks for Lung Pattern Analysis
    Christodoulidis, Stergios
    Anthimopoulos, Marios
    Ebner, Lukas
    Christe, Andreas
    Mougiakakou, Stavroula
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2017, 21 (01) : 76 - 84
  • [48] Definition of Unique Objects by Convolutional Neural Networks using Transfer Learning
    Rusakov K.D.
    Seliverstov D.E.
    Osipov V.V.
    Reshetnikov V.N.
    International Journal of Advanced Computer Science and Applications, 2020, 11 (11): : 48 - 54
  • [49] CLASSIFICATION OF HAZE IN CITY IMAGES WITH CONVOLUTIONAL NEURAL NETWORKS AND TRANSFER LEARNING
    Isikdag, U.
    Apak, S.
    JOURNAL OF ENVIRONMENTAL PROTECTION AND ECOLOGY, 2021, 22 (04): : 1379 - 1385
  • [50] Efficient transfer learning for multi-channel convolutional neural networks
    de La Comble, Alois
    Prepin, Ken
    PROCEEDINGS OF 17TH INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS (MVA 2021), 2021,