参考资料:[1] Google 为你复活巴赫, https://mp.weixin.qq.com/s/wFcCnzRnI4mPIDOYD1X8yA [2] Counterpoint by Convolution, https://arxiv.org/abs/1903.07227 [3] Music Transformer, https://arxiv.org/abs/1809.04281 [4] The Bach Doodle: Approachable music composition with machine learning at scale, https://arxiv.org/abs/1907.06637 [5] Coconet: the ML model behind today’s Bach Doodle, https://magenta.tensorflow.org/coconet [6] Music Transformer: Generating Music with Long-Term Structure, https://magenta.tensorflow.org/music-transformer [7] 详解Transformer (Attention Is All You Need), https://zhuanlan.zhihu.com/p/48508221 [8] 谷歌机器学习模型新进展:生成时长更长且连贯的音乐, https://cloud.tencent.com/developer/article/1380289 [9] 谷歌发布音乐 AI Doodle 庆祝巴赫生日,这里是它背后的技术, https://www.leiphone.com/news/201904/GQYJhhj91UdjSV2P.html [11] 巴赫诞辰纪念 Doodle, https://www.google.com/doodles/celebrating-johann-sebastian-bach