基于Transformers的吉他弹拨自动合成及槽型建模
Automatic Composition of Guitar Tabs by Transformers and Groove Modeling
摘要：
深度学习算法越来越多地被开发用于学习以MIDI文件的形式创作音乐。然而，这种算法是否能很好地用于编写吉他标签，这与MIDI有很大的不同，仍然相对未被探索。为了解决这个问题，我们构建了一个模型，用于使用Transformer-XL（一种神经序列模型架构）编写指弹吉他标签。在这个模型中，我们探讨了以下研究问题。首先，神经网络是否生成具有有意义的音符-字符串组合的音符序列，这对吉他很重要，但对钢琴等其他乐器则不重要。第二，它是否能产生具有连贯节奏的作品，这对指弹吉他音乐至关重要。最后，与真实的人造作品相比，创作的音乐是多么令人愉快。我们的工作提供了深度学习对标签组成的承诺的初步经验证据，并建议了未来研究的领域。
英文摘要：
Deep learning algorithms are increasingly developed for learning to compose music in the form of MIDI files. However, whether such algorithms work well for composing guitar tabs, which are quite different from MIDIs, remain relatively unexplored. To address this, we build a model for composing fingerstyle guitar tabs with Transformer-XL, a neural sequence model architecture. With this model, we investigate the following research questions. First, whether the neural net generates note sequences with meaningful note-string combinations, which is important for the guitar but not other instruments such as the piano. Second, whether it generates compositions with coherent rhythmic groove, crucial for fingerstyle guitar music. And, finally, how pleasant the composed music is in comparison to real, human-made compositions. Our work provides preliminary empirical evidence of the promise of deep learning for tab composition, and suggests areas for future study.
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。
