Guardado en:
Detalles Bibliográficos
Autores principales: Kouteili, Sam, Madhu, Hiren, Typaldos, George, Santolucito, Mark
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2508.05473
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909802700996608
author Kouteili, Sam
Madhu, Hiren
Typaldos, George
Santolucito, Mark
author_facet Kouteili, Sam
Madhu, Hiren
Typaldos, George
Santolucito, Mark
contents LLM-powered code generation has the potential to revolutionize creative coding endeavors, such as live-coding, by enabling users to focus on structural motifs over syntactic details. In such domains, when prompting an LLM, users may benefit from considering multiple varied code candidates to better realize their musical intentions. Code generation models, however, struggle to present unique and diverse code candidates, with no direct insight into the code's audio output. To better establish a relationship between code candidates and produced audio, we investigate the topology of the mapping between code and audio embedding spaces. We find that code and audio embeddings do not exhibit a simple linear relationship, but supplement this with a constructed predictive model that shows an embedding alignment map could be learned. Supplementing the aim for musically diverse output, we present a model that given code predicts output audio embedding, constructing a code-audio embedding alignment map.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05473
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Embedding Alignment in Code Generation for Audio
Kouteili, Sam
Madhu, Hiren
Typaldos, George
Santolucito, Mark
Multimedia
Artificial Intelligence
Sound
Audio and Speech Processing
LLM-powered code generation has the potential to revolutionize creative coding endeavors, such as live-coding, by enabling users to focus on structural motifs over syntactic details. In such domains, when prompting an LLM, users may benefit from considering multiple varied code candidates to better realize their musical intentions. Code generation models, however, struggle to present unique and diverse code candidates, with no direct insight into the code's audio output. To better establish a relationship between code candidates and produced audio, we investigate the topology of the mapping between code and audio embedding spaces. We find that code and audio embeddings do not exhibit a simple linear relationship, but supplement this with a constructed predictive model that shows an embedding alignment map could be learned. Supplementing the aim for musically diverse output, we present a model that given code predicts output audio embedding, constructing a code-audio embedding alignment map.
title Embedding Alignment in Code Generation for Audio
topic Multimedia
Artificial Intelligence
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2508.05473