Título:
Music proofreading with RefinPaint : Where and how to modify compositions given context.
Otros títulos:
Coordinador:
Director:
Compilador:
Autor:
Ramoneda, Pedro
Rocamora, Martín
Akama, Taketo
Rocamora, Martín
Akama, Taketo
Tutor:
Tipo de documento:
Ponencia
Editor:
Palabras clave:
Creativity
Creativity and learning
Generative tasks
Interactions
MIR tasks
Music generation
Human-ai co-creativity
Creativity and learning
Generative tasks
Interactions
MIR tasks
Music generation
Human-ai co-creativity
Descriptores:
Año de publicación:
2024
Contenido:
Resumen:
Autoregressive generative transformers are key in music generation, producing coherent compositions but facing challenges in human-machine collaboration. We propose RefinPaint, an iterative technique that improves the sampling process. It does this by identifying the weaker music elements using a feedback model, which then informs the choices for resampling by an inpainting model. This dual-focus methodology not only facilitates the machine's ability to improve its automatic inpainting generation through repeated cycles but also offers a valuable tool for humans seeking to refine their compositions with automatic proofreading. Experimental results suggest RefinPaint's effectiveness in inpainting and proofreading tasks, demonstrating its value for refining music created by both machines and humans. This approach not only facilitates creativity but also aids amateur composers in improving their work.
Descripción:
metadata.articulos.dc.description.uri:
Editorial:
ISMIR
EN:
25th International Society for Music Information Retrieval (ISMIR), San Francisco, California, United States, 10-14 nov 2024, pp. 1-8.
Financiadores:
Citación:
Ramoneda, P., Rocamora, M. y Akama, T. Music proofreading with RefinPaint : Where and how to modify compositions given context [en línea]. EN: 25th International Society for Music Information Retrieval (ISMIR), San Francisco, California, United States, 10-14 nov 2024, pp 1-8.
Citación:
metadata.articulos.cc.license.name:
ISBN:
e-ISBN:
ISSN:
ISMN:
Otros identificadores:
Cobertura geográfica:
Cobertura temporal:
Departamento académico:
Procesamiento de Señales
Grupo de investigación:
Procesamiento de Audio (GPA)
Licencia:
Licencia Creative Commons Atribución (CC - By 4.0)
Colecciones:
| Ficheros | Descripción | Tamaño | Formato | ||
|---|---|---|---|---|---|
| RRA24.pdf | Versión publicada | 768.97 KB | Adobe PDF |