{"title":"大家作曲:深节拍音乐","authors":"Conghao Shen, Violet Z. Yao, Yixin Liu","doi":"10.1145/3587819.3592542","DOIUrl":null,"url":null,"abstract":"This project presents a deep learning approach to generate monophonic melodies based on input beats, allowing even amateurs to create their own music compositions. Three effective methods - LSTM with Full Attention, LSTM with Local Attention, and Transformer with Relative Position Representation - are proposed for this novel task, providing great variation, harmony, and structure in the generated music. This project allows anyone to compose their own music by tapping their keyboards or \"recoloring\" beat sequences from existing works.","PeriodicalId":330983,"journal":{"name":"Proceedings of the 14th Conference on ACM Multimedia Systems","volume":"154 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Everybody Compose: Deep Beats To Music\",\"authors\":\"Conghao Shen, Violet Z. Yao, Yixin Liu\",\"doi\":\"10.1145/3587819.3592542\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This project presents a deep learning approach to generate monophonic melodies based on input beats, allowing even amateurs to create their own music compositions. Three effective methods - LSTM with Full Attention, LSTM with Local Attention, and Transformer with Relative Position Representation - are proposed for this novel task, providing great variation, harmony, and structure in the generated music. This project allows anyone to compose their own music by tapping their keyboards or \\\"recoloring\\\" beat sequences from existing works.\",\"PeriodicalId\":330983,\"journal\":{\"name\":\"Proceedings of the 14th Conference on ACM Multimedia Systems\",\"volume\":\"154 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 14th Conference on ACM Multimedia Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3587819.3592542\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 14th Conference on ACM Multimedia Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3587819.3592542","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
This project presents a deep learning approach to generate monophonic melodies based on input beats, allowing even amateurs to create their own music compositions. Three effective methods - LSTM with Full Attention, LSTM with Local Attention, and Transformer with Relative Position Representation - are proposed for this novel task, providing great variation, harmony, and structure in the generated music. This project allows anyone to compose their own music by tapping their keyboards or "recoloring" beat sequences from existing works.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
