基于深度学习的旋律属性评分模型  

Melody attribute scoring model based on deep learning

作　　者：刘硕 姚望舒[1] Liu Shuo;Yao Wangshu(College of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215031,China)

机构地区：[1]苏州大学计算机科学与技术学院,江苏苏州215031

出　　处：《计算机时代》2025年第1期42-45,共4页Computer Era

摘　　要：针对一段旋律的乐谱推荐问题,提出一种基于深度学习评估其旋律属性的方法。评估得到的属性评分可以作为歌曲的音乐标签,这样就可以根据用户的历史听歌数据来做出精准推荐,即推荐符合用户喜好的音乐。提出了一种利用该模型指导音乐生成模型进行精准音乐生成的方法,为如何提高当下AI作曲精准性和用户可定制性的问题提供了一个参考方案。This paper proposes a method based on deep learning to evaluate the melody attributes of music.The attribute score obtained by the evaluation can be used as the music label of the song,so that accurate recommendations can be made based on the user's historical listening data,that is,recommending music that matches the user's preferences.A method of using the model to guide the music generation model for accurate music generation is proposed,which provides a solution to the problem of how to improve the AI composition accuracy and user customizability of current.

关 键 词：旋律属性评分 音乐分析 深度学习 长短期记忆网络 卷积神经网络 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]