Style-Conditioned Music Generation

Lim, Yu-Quan; Chan, Chee Seng; Loo, Fung Ying

doi:10.1109/icme46284.2020.9102870

Cited by 10 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First investigated in applications that target computer vision, music style transfer has recently shown promising results in both the audio [37] and symbolic domains [38][39][40]. As a prospective application of DadaGP, we envisage that genre information can be leveraged in segregating the dataset across different genres, rendering it suitable for the task of musical genre style transfer, as proposed in [41] for the specific morphing between Bach chorales and Western folk tunes. Furthermore, besides musical genre, artistic information can also be used towards the task of composer style transfer, once again by filtering DadaGP across distinct artists.…”

Section: Music Style Transfermentioning

confidence: 99%

DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models

Sarmento,

Kumar,

Carr

et al. 2021

Preprint

View full text Add to dashboard Cite

Originating in the Renaissance and burgeoning in the digital era, tablatures are a commonly used music notation system which provides explicit representations of instrument fingerings rather than pitches. GuitarPro has established itself as a widely used tablature format and software enabling musicians to edit and share songs for musical practice, learning, and composition. In this work, we present DadaGP, a new symbolic music dataset comprising 26,181 song scores in the GuitarPro format covering 739 musical genres, along with an accompanying tokenized format well-suited for generative sequence models such as the Transformer. The tokenized format is inspired by event-based MIDI encodings, often used in symbolic music generation models. The dataset is released with an encoder/decoder which converts GuitarPro files to tokens and back. We present results of a use case in which DadaGP is used to train a Transformer-based model to generate new songs in GuitarPro format. We discuss other relevant use cases for the dataset (guitar-bass transcription, music style transfer and artist/genre classification) as well as ethical implications. DadaGP opens up the possibility to train GuitarPro score generators, fine-tune models on custom data, create new styles of music, AI-powered songwriting apps, and human-AI improvisation.

show abstract