Design of Semiautomatic Digital Creation System for Electronic Music Based on Recurrent Neural Network

Computational Intelligence and Neuroscience - Tập 2022 - Trang 1-12 - 2022
Yonghui Duan1, Jianping Wang2
1School of Music and Dance of Changzhi University, Changzhi, Shanxi 046011, China
2Department of Intelligence and Automation of Taiyuan University, Taiyuan, Shanxi 030032, China

Tóm tắt

Semiautomated digital creation is increasingly important in the manipulation of electronic music. How to realize the learning of local effective features of audio data is a difficult point in the current research field. Based on recurrent neural network theory, this paper designs a semiautomatic digital creation system for electronic music for digital manipulation and genre classification. The recurrent neural network improves the transmission of electronic music information between the input and output of the network by adopting dense connections consistent with DenseNet and adopts an inception-like structure for the autonomous selection of effective recursive nuclear electronic music categories. In the simulation process, the prediction method based on semiautomatic digital audio clips is also adopted, which pays more attention to the learning of local effective features of audio data, which gives the model the ability to create audio samples of different lengths and improves the model’s support for creative tasks in different scenarios. It includes the determination of the number of neurons, the selection of the function of neurons, the determination of the connection method, and the specific learning algorithm rules, and then the training samples are formed. The experimental results show that the recurrent neural network exhibits powerful feature extraction ability and classification ability of music information. The 10-fold cross-validation on GTZAN dataset and ISMIR2004 dataset has obtained 88.7% and 87.68%, surpassing similar ones. The model has reached a leading level. After further use of the MSD (Million Song Dataset) dataset for pre-semiautomatic training, the model effect has been further greatly improved. The accuracy rate on the dataset has been increased to 91.0% and 89.91%, respectively, which has improved the semiautomatic number and creative advancement.

Từ khóa


Tài liệu tham khảo

10.3390/ijgi11030197

10.1016/j.jtte.2021.03.005

A. M. A. Mraz, Development of the localized road damage detection model using deep neural network, 4

10.1117/12.2293518

10.1080/2573234x.2021.1908861

10.1109/ACCESS.2022.3159618

10.1016/j.ecoinf.2021.101310

10.3390/agronomy11040667

R. L. Curier, 2018, Monitoring spatial sustainable development: Semi-automated analysis of satellite and aerial images for energy transition and sustainability indicators, IEEE Access, 8

10.1016/j.compbiomed.2021.104873

10.3390/app12031353

10.1101/2021.12.01.470811

10.1016/j.ijrmms.2021.104981

10.1177/0361198120944926

10.1007/978-3-030-22354-0_47

10.1007/s00530-020-00694-1

10.1109/COMPSAC.2018.00058

10.1016/j.eswa.2022.116616

10.1109/access.2020.2991187

10.1016/j.future.2021.11.018

10.2478/jdis-2020-0003

10.1007/s11831-021-09559-w

10.1109/tnnls.2020.2995800

10.1109/jbhi.2020.3004143

10.1016/j.eswa.2021.115406

10.1109/SIBGRAPI.2018.00012

Thông tin
Thông tin xuất bản

Computational Intelligence and Neuroscience

Tập 2022

1-12

Thông tin tác giả