{"title":"基于深度神经网络的音乐旋律特征提取与识别","authors":"Zhong‐Jiang Zhang","doi":"10.21595/jve.2023.23075","DOIUrl":null,"url":null,"abstract":"The music melody can be used to distinguish the genre style of music and can also be used for retrieving music works. This paper used a deep learning algorithm, the convolutional neural network (CNN), to extract the features of musical melodies and recognize genres. Three-tuple samples were used as training samples in the training process. Orthogonal experiments were conducted on the number of music segments and the type of activation function in the algorithm in the simulation experiments. The CNN algorithm was compared with support vector machine (SVM) and traditional CNN algorithms. The results showed that there were obvious differences in the pitch and melody curves of different genres of music; the recognition performance was best when the number of music segments was six and the activation function was relu; the CNN algorithm trained by three-tuple samples had better recognition accuracy and spent less recognition time.","PeriodicalId":49956,"journal":{"name":"Journal of Vibroengineering","volume":" ","pages":""},"PeriodicalIF":0.7000,"publicationDate":"2023-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Extraction and recognition of music melody features using a deep neural network\",\"authors\":\"Zhong‐Jiang Zhang\",\"doi\":\"10.21595/jve.2023.23075\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The music melody can be used to distinguish the genre style of music and can also be used for retrieving music works. This paper used a deep learning algorithm, the convolutional neural network (CNN), to extract the features of musical melodies and recognize genres. Three-tuple samples were used as training samples in the training process. Orthogonal experiments were conducted on the number of music segments and the type of activation function in the algorithm in the simulation experiments. The CNN algorithm was compared with support vector machine (SVM) and traditional CNN algorithms. The results showed that there were obvious differences in the pitch and melody curves of different genres of music; the recognition performance was best when the number of music segments was six and the activation function was relu; the CNN algorithm trained by three-tuple samples had better recognition accuracy and spent less recognition time.\",\"PeriodicalId\":49956,\"journal\":{\"name\":\"Journal of Vibroengineering\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":0.7000,\"publicationDate\":\"2023-03-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Vibroengineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.21595/jve.2023.23075\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, MECHANICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Vibroengineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.21595/jve.2023.23075","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
Extraction and recognition of music melody features using a deep neural network
The music melody can be used to distinguish the genre style of music and can also be used for retrieving music works. This paper used a deep learning algorithm, the convolutional neural network (CNN), to extract the features of musical melodies and recognize genres. Three-tuple samples were used as training samples in the training process. Orthogonal experiments were conducted on the number of music segments and the type of activation function in the algorithm in the simulation experiments. The CNN algorithm was compared with support vector machine (SVM) and traditional CNN algorithms. The results showed that there were obvious differences in the pitch and melody curves of different genres of music; the recognition performance was best when the number of music segments was six and the activation function was relu; the CNN algorithm trained by three-tuple samples had better recognition accuracy and spent less recognition time.
期刊介绍:
Journal of VIBROENGINEERING (JVE) ISSN 1392-8716 is a prestigious peer reviewed International Journal specializing in theoretical and practical aspects of Vibration Engineering. It is indexed in ESCI and other major databases. Published every 1.5 months (8 times yearly), the journal attracts attention from the International Engineering Community.