用吉他谱生成逼真电音，通过流匹配与风格迁移提升表现力。
GuitarFlow: Realistic Electric Guitar Synthesis From Tablatures via Flow Matching and Style Transfer
- 先用简化的虚拟乐器渲染谱子，再用流匹配进行风格迁移。
- 仅需6小时训练数据，生成音频真实感显著提升。
- 适合音乐生成、电吉他合成及符号化演奏研究者。
近年来，人工智能在音频域的音乐生成方面取得了稳步进展。然而对于吉他等乐器，可控的乐器合成在表现力上仍受限。我们提出GuitarFlow，一种专为电吉他合成设计的模型。生成过程以吉他谱（tablature）为引导，该符号格式直观且能有效表达弯音、闷音、连奏等吉他特有技巧，相较MIDI等通用记谱法更优。模型首先使用简单的基于样本的虚拟乐器将吉他谱转为音频，再通过流匹配技术实现风格迁移，将虚拟音色转化为更逼真的声音。该方法训练和推理速度快，仅需不到6小时的训练数据。我们通过客观指标与听觉测试验证了生成音色在真实感上的显著提升。
原文摘要 · Abstract (English)
Music generation in the audio domain using artificial intelligence (AI) has witnessed steady progress in recent years. However for some instruments, particularly the guitar, controllable instrument synthesis remains limited in expressivity. We introduce GuitarFlow, a model designed specifically for electric guitar synthesis. The generative process is guided using tablatures, an ubiquitous and intuitive guitar-specific symbolic format. The tablature format easily represents guitar-specific playing techniques (e.g. bends, muted strings and legatos), which are more difficult to represent in other common music notation formats such as MIDI. Our model relies on an intermediary step of first rendering the tablature to audio using a simple sample-based virtual instrument, then performing style transfer using Flow Matching in order to transform the virtual instrument audio into more realistic sounding examples. This results in a model that is quick to train and to perform inference, requiring less than 6 hours of training data. We present the results of objective evaluation metrics, together with a listening test, in which we show significant improvement in the realism of the generated guitar audio from tablatures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。