基于XLNet和音乐专用位置编码的变长乐谱填充
Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding
摘要：
本文提出了一种新的基于自我注意力的乐谱填充模型，以产生一个复调音乐序列，填补了给定的过去和未来背景之间的空白。虽然现有的方法只能用固定数量的音符填充一小段，或者在过去和未来的上下文之间填充固定的时间跨度，但我们的模型可以为不同的时间跨度填充可变数量的音符（最多128个）。我们通过三个主要的技术贡献来实现这一目标。首先，我们将XLNet（一种最初用于无监督模型预训练的自回归模型）用于乐谱填充。其次，我们提出了一种新的，音乐专业的位置编码称为相对酒吧编码，更好地通知模型的音符的位置在过去和未来的背景。第三，为了使相对条形编码大写，我们执行前瞻起始预测以在预测音符的其他属性之前预测音符的起始一个时间步。我们将我们提出的模型与两个强基线进行了比较，结果表明我们的模型在客观和主观分析方面都更优越。
英文摘要：
This paper proposes a new self-attention based model for music score infilling, i.e., to generate a polyphonic music sequence that fills in the gap between given past and future contexts. While existing approaches can only fill in a short segment with a fixed number of notes, or a fixed time span between the past and future contexts, our model can infill a variable number of notes (up to 128) for different time spans. We achieve so with three major technical contributions. First, we adapt XLNet, an autoregressive model originally proposed for unsupervised model pre-training, to music score infilling. Second, we propose a new, musically specialized positional encoding called relative bar encoding that better informs the model of notes' position within the past and future context. Third, to capitalize relative bar encoding, we perform look-ahead onset prediction to predict the onset of a note one time step before predicting the other attributes of the note. We compare our proposed model with two strong baselines and show that our model is superior in both objective and subjective analyses.
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。
