KDD论文推荐|XiaoIce Band：流行音乐的旋律与编曲生成框架
国际知识发现与数据挖掘大会（ACM SIGKDD Conference on Knowledge Discovery and Data Mining,简称SIGKDD）是数据挖掘领域的顶级国际会议。我们将持续对近年KDD的部分论文进行解读。
KDD 2018共收到投稿论文1479篇，其中研究性论文983篇，应用数据科学论文496篇，均创下新高。本文选取了KDD 2018最佳学生论文奖获奖论文进行介绍：
论文题目
XiaoIce Band:A Melody and Arrangement Generation Framework for Pop Music
作者
Hongyuan Zhu、Qi Liu、Nicholas Jing Yuan、Chuan Qin、Jiawei Li、Kun Zhang、Guang Zhou、Furu Wei、Yuanchun Xu、Enhong Chen
会议／年份
SIGKDD 2018
链接（点击阅读原文也可获取）
https://www.aminer.cn/archive/xiaoice-band-a-melody-and arrangement-generation-framework-for-pop music/5b67b45517c44aac1c8607e9
Abstract
With the development of knowledge of music composition and the recent increase in demand, an increasing number of companies and research institutes have begun to study the automatic generation of music. However, previous models have limitations when applying to song generation, which requires both the melody and arrangement. Besides, many critical factors related to the quality of a song such as chord progression and rhythm patterns are not well addressed. In particular, the problem of how to ensure the harmony of multi-track music is still underexplored. To this end, we present a focused study on pop music generation, in which we take both chord and rhythm influence of melody generation and the harmony of music arrangement into consideration. We propose an end-to-end melody and arrangement generation framework, called XiaoIce Band, which generates a melody track with several accompany tracks played by several types of instruments. Specifically, we devise a Chord based Rhythm and Melody Cross-Generation Model (CRMCG) to generate melody with chord progressions. Then, we propose a Multi-Instrument Co-Arrangement Model (MICA) using multi-task learning for multi-track music arrangement. Finally, we conduct extensive experiments on a real-world dataset, where the results demonstrate the effectiveness of XiaoIce Band.
摘要
音乐对人们的生活有着重要的影响。然而，创作音乐需要大量的专业知识和技能。近年来，如何利用机器学习技术自动进行音乐创作成为人工智能领域的热门话题。由于音乐元素的复杂性，如歌曲不同的和弦进行、乐段中结构鲜明的节奏型、不同特性的音轨（乐器）需要保持和谐一致等，使得高质量的单音轨作曲、多音轨编曲算法的设计充满了挑战性与特殊性。为此，论文基于深度神经网络和多任务学习等方法，从历史音乐数据（如十万多首歌曲）中学习音乐的音程关系、结构以及各种乐器的演绎特色，设计了一种基于和弦的节奏和旋律交叉的生成模型（CRMCG）来产生带有和弦进行的旋律；更进一步，通过构建多个任务（即多个音轨，乐器序列）关联模型，为乐器的相互配合搭建了信息交互的桥梁，实现了一种多乐器联合编曲模型(MICA)。
