arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.03392eess.AS
收藏

增强型记忆网络:一种用于符号音乐生成的新型网络结构

Enhanced Memory Network: The novel network structure for Symbolic Music Generation

Jin Li, Haibin Liu, Nan Yan, Lan Wang

摘要:

符号旋律的生成是音乐自动生成的重要任务之一。最近,基于神经网络的模型对生成象征性旋律产生了重大影响。然而,通过深度神经网络捕获音乐上下文结构是复杂的。虽然长短期记忆(LSTM)试图通过学习音乐序列中的顺序依赖性来解决这个问题,但它无法在LSTM的每个时间步仅输入一个音符的情况下捕获音乐上下文。在本文中,我们提出了一种新的具有多个循环单元的增强记忆网络(EMN),称为增强记忆单元(EMU),以显式修改LSTM的内部架构,以包含音乐节拍信息,并通过在记忆门内聚合节拍来加强对最新音乐节拍的记忆。此外,为了增加所生成的音符的多样性,隐藏状态的相邻时间步长之间的余弦距离被认为是损失函数的一部分,以避免损害所生成的音符的多样性的高相似性分数。客观和主观评价结果表明,该方法达到了最先进的性能。代码和音乐演示可在https://github.com/qrqrqrqr/EMU上获得

英文摘要:

Symbolic melodies generation is one of the essential tasks for automatic music generation. Recently, models based on neural networks have had a significant influence on generating symbolic melodies. However, the musical context structure is complicated to capture through deep neural networks. Although long short-term memory (LSTM) is attempted to solve this problem through learning order dependence in the musical sequence, it is not capable of capturing musical context with only one note as input for each time step of LSTM. In this paper, we propose a novel Enhanced Memory Network (EMN) with several recurrent units, named Enhanced Memory Unit (EMU), to explicitly modify the internal architecture of LSTM for containing music beat information and reinforces the memory of the latest musical beat through aggregating beat inside the memory gate. In addition, to increase the diversity of generated musical notes, cosine distance among adjacent time steps of hidden states is considered as part of loss functions to avoid a high similarity score that harms the diversity of generated notes. Objective and subjective evaluation results show that the proposed method achieves state-of-the-art performance. Code and music demo are available at https://github.com/qrqrqrqr/EMU

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。

↑