论文标题
音乐发电的注意网络
Attentional networks for music generation
论文作者
论文摘要
现实的音乐发电一直是一个具有挑战性的问题，因为它可能缺乏结构或理性。在这项工作中，我们提出了一种基于深度学习的音乐生成方法，以制作旧式音乐，尤其是爵士乐，并使用双向长期记忆（BI-LSTM）神经网络重新旋转旋律结构，并引起人们的注意。由于成功地建模了连续数据中的长期时间依赖性及其在视频中成功的成功，因此BI-LSTMS具有注意力为音乐发电中的自然选择和早期利用。我们在实验中验证了BI-LSTM的注意力，能够保留演奏音乐的丰富性和技术细微差别。
Realistic music generation has always remained as a challenging problem as it may lack structure or rationality. In this work, we propose a deep learning based music generation method in order to produce old style music particularly JAZZ with rehashed melodic structures utilizing a Bi-directional Long Short Term Memory (Bi-LSTM) Neural Network with Attention. Owing to the success in modelling long-term temporal dependencies in sequential data and its success in case of videos, Bi-LSTMs with attention serve as the natural choice and early utilization in music generation. We validate in our experiments that Bi-LSTMs with attention are able to preserve the richness and technical nuances of the music performed.
