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 2301.01162cs.SDcs.CLeess.AS
收藏

语言模型是鼓手:基于自然语言预训练的鼓点作曲

Language Models are Drummers: Drum Composition with Natural Language Pre-Training

University of Pennsylvania(宾夕法尼亚大学)

Li Zhang, Chris Callison-Burch

摘要:

使用人工智能自动音乐生成通常需要大量数据,对于许多不太常见的流派和乐器来说,这是很难获得的。为了解决这个问题,我们提出了正在进行的工作和初步发现,即通过微调在仅数百个MIDI文件的海量文本语料库上预训练的大语言模型,深度模型将知识从语言转移到音乐的可能性。鼓表演。我们证明,通过这样做,最大的,最先进的模型之一(GPT3)能够生成合理的鼓槽,而没有预先训练的模型(Transformer)除了天真的重复之外没有显示出这种能力。评估生成的音乐是一项具有挑战性的任务,更是评估鼓槽在文献中很少有先例。因此,我们提出了一种量身定制的结构评估方法,并分析了GPT3产生的鼓槽与人类专业人士演奏的鼓槽相比,揭示了语言到音乐转换的优势和劣势。我们的研究结果表明,语言到音乐迁移学习与大语言模型是可行的,有前途的。

英文摘要:

Automatic music generation with artificial intelligence typically requires a large amount of data which is hard to obtain for many less common genres and musical instruments. To tackle this issue, we present ongoing work and preliminary findings on the possibility for deep models to transfer knowledge from language to music, by finetuning large language models pre-trained on a massive text corpus on only hundreds of MIDI files of drum performances. We show that by doing so, one of the largest, state-of-the-art models (GPT3) is capable of generating reasonable drum grooves, while models that are not pre-trained (Transformer) shows no such ability beyond naive repetition. Evaluating generated music is a challenging task, more so is evaluating drum grooves with little precedence in literature. Hence, we propose a tailored structural evaluation method and analyze drum grooves produced by GPT3 compared to those played by human professionals, exposing the strengths and weaknesses of such generation by language-to-music transfer. Our findings suggest that language-to-music transfer learning with large language models is viable and promising.

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。

↑