GuitarFlow: Realistic Electric Guitar Synthesis From Tablatures via Flow Matching and Style Transfer
This addresses the challenge of generating expressive and realistic electric guitar audio from tablatures for musicians and AI music applications, though it is incremental as it builds on existing flow matching and style transfer techniques.
The authors tackled the problem of limited expressivity in controllable electric guitar synthesis by introducing GuitarFlow, a model that uses tablatures and flow matching with style transfer to generate realistic audio, achieving significant improvement in realism as shown in objective metrics and listening tests.
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.