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 2209.08212cs.SDcs.AIcs.MMeess.AS
收藏

作曲与修饰:通过两阶段方法生成结构良好的钢琴演奏

Compose & Embellish: Well-Structured Piano Performance Generation via A Two-Stage Approach

Taiwan AI Labs(台湾人工智能实验室);Carnegie Mellon University(卡内基梅隆大学);Academia Sinica(中央研究院)

Shih-Lun Wu, Yi-Hsuan Yang

摘要:

即使使用像Transformers这样的强序列模型,生成具有长距离音乐结构的富有表现力的钢琴演奏仍然具有挑战性。与此同时,方法来组成结构良好的旋律或铅片(旋律+和弦),即,简单的音乐形式,获得了更多的成功。观察上述情况,我们设计了一个两阶段的基于transformer的框架,首先组成一个铅表,然后用伴奏和表达性的触摸来修饰它。这样的因子分解也可以在非钢琴数据上进行预训练。我们的客观和主观实验表明,作曲与修饰缩小了一半的艺术和真实表演之间的结构性差距,并提高了其他音乐方面,如丰富性和连贯性。

英文摘要:

Even with strong sequence models like Transformers, generating expressive piano performances with long-range musical structures remains challenging. Meanwhile, methods to compose well-structured melodies or lead sheets (melody + chords), i.e., simpler forms of music, gained more success. Observing the above, we devise a two-stage Transformer-based framework that Composes a lead sheet first, and then Embellishes it with accompaniment and expressive touches. Such a factorization also enables pretraining on non-piano data. Our objective and subjective experiments show that Compose & Embellish shrinks the gap in structureness between a current state of the art and real performances by half, and improves other musical aspects such as richness and coherence as well.

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。

↑