arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1604.05358cs.AIcs.MM
收藏

基于文本的LSTM自动作曲网络

Text-based LSTM networks for Automatic Music Composition

Queen Mary University of London(伦敦玛丽女王大学)

Keunwoo Choi, George Fazekas, Mark Sandler

摘要:

在本文中,我们介绍了新的方法,并讨论了基于文本的LSTM(长短期记忆)网络自动音乐合成的结果。建议的网络被设计为学习在两个案例研究中表示和弦进行和鼓轨道的文本文档内的关系。在实验中,单词RNN(递归神经网络)在这两种情况下都显示出良好的结果,而基于字符的RNN(char-RNN)只能成功学习和弦进行。所提出的系统可以用于全自动合成或作为半自动系统,帮助人类通过控制模型的多样性参数来创作音乐。

英文摘要:

In this paper, we introduce new methods and discuss results of text-based LSTM (Long Short-Term Memory) networks for automatic music composition. The proposed network is designed to learn relationships within text documents that represent chord progressions and drum tracks in two case studies. In the experiments, word-RNNs (Recurrent Neural Networks) show good results for both cases, while character-based RNNs (char-RNNs) only succeed to learn chord progressions. The proposed system can be used for fully automatic composition or as semi-automatic systems that help humans to compose music by controlling a diversity parameter of the model.

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。

↑