arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.01973cs.SDcs.LGeess.ASstat.ML
收藏

基于LSTM神经网络和强化学习的复调音乐创作

Polyphonic Music Composition with LSTM Neural Networks and Reinforcement Learning

Indian Institute of Technology, Madras(印度理工学院马德拉斯分校)

Harish Kumar, Balaraman Ravindran

摘要:

在算法音乐作曲领域,机器学习驱动的系统消除了对精心手工制作作曲规则的需要。特别是,循环神经网络学习复杂时间模式的能力很适合音乐领域。在最近使用深度RNN进行音乐作曲的一些尝试中,已经观察到了有希望的结果。这些方法通常旨在首先训练神经网络以再现从现有歌曲中提取的连续性。随后,它们被用于在音频样本级或音符级上作曲。我们设计了一种将复调音乐分成少量单声道流的表示法。这种表示法大大降低了问题的复杂性,并消除了指数数量的可能较差的组合物。在我们的LSTM神经网络学习这种表示的音乐序列的基础上,我们构建了一个RL代理,它学习寻找歌曲的组合,这些组合的联合优势产生了令人愉快的作品。我们介绍Amadeus,一个算法音乐作曲系统,它可以创作由复杂的旋律,基本和弦,甚至偶尔对位序列组成的音乐。

英文摘要:

In the domain of algorithmic music composition, machine learning-driven systems eliminate the need for carefully hand-crafting rules for composition. In particular, the capability of recurrent neural networks to learn complex temporal patterns lends itself well to the musical domain. Promising results have been observed across a number of recent attempts at music composition using deep RNNs. These approaches generally aim at first training neural networks to reproduce subsequences drawn from existing songs. Subsequently, they are used to compose music either at the audio sample-level or at the note-level. We designed a representation that divides polyphonic music into a small number of monophonic streams. This representation greatly reduces the complexity of the problem and eliminates an exponential number of probably poor compositions. On top of our LSTM neural network that learnt musical sequences in this representation, we built an RL agent that learnt to find combinations of songs whose joint dominance produced pleasant compositions. We present Amadeus, an algorithmic music composition system that composes music that consists of intricate melodies, basic chords, and even occasional contrapuntal sequences.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑