Language Models for Music Medicine Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nikolakakis, Emmanouil, Ching, Joann, Karystinaios, Emmanouil, Sipin, Gabrielle, Widmer, Gerhard, Marinescu, Razvan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913577865052160
author Nikolakakis, Emmanouil
Ching, Joann
Karystinaios, Emmanouil
Sipin, Gabrielle
Widmer, Gerhard
Marinescu, Razvan
author_facet Nikolakakis, Emmanouil
Ching, Joann
Karystinaios, Emmanouil
Sipin, Gabrielle
Widmer, Gerhard
Marinescu, Razvan
contents Music therapy has been shown in recent years to provide multiple health benefits related to emotional wellness. In turn, maintaining a healthy emotional state has proven to be effective for patients undergoing treatment, such as Parkinson's patients or patients suffering from stress and anxiety. We propose fine-tuning MusicGen, a music-generating transformer model, to create short musical clips that assist patients in transitioning from negative to desired emotional states. Using low-rank decomposition fine-tuning on the MTG-Jamendo Dataset with emotion tags, we generate 30-second clips that adhere to the iso principle, guiding patients through intermediate states in the valence-arousal circumplex. The generated music is evaluated using a music emotion recognition model to ensure alignment with intended emotions. By concatenating these clips, we produce a 15-minute "music medicine" resembling a music therapy session. Our approach is the first model to leverage Language Models to generate music medicine. Ultimately, the output is intended to be used as a temporary relief between music therapy sessions with a board-certified therapist.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09080
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Language Models for Music Medicine Generation
Nikolakakis, Emmanouil
Ching, Joann
Karystinaios, Emmanouil
Sipin, Gabrielle
Widmer, Gerhard
Marinescu, Razvan
Sound
Audio and Speech Processing
Music therapy has been shown in recent years to provide multiple health benefits related to emotional wellness. In turn, maintaining a healthy emotional state has proven to be effective for patients undergoing treatment, such as Parkinson's patients or patients suffering from stress and anxiety. We propose fine-tuning MusicGen, a music-generating transformer model, to create short musical clips that assist patients in transitioning from negative to desired emotional states. Using low-rank decomposition fine-tuning on the MTG-Jamendo Dataset with emotion tags, we generate 30-second clips that adhere to the iso principle, guiding patients through intermediate states in the valence-arousal circumplex. The generated music is evaluated using a music emotion recognition model to ensure alignment with intended emotions. By concatenating these clips, we produce a 15-minute "music medicine" resembling a music therapy session. Our approach is the first model to leverage Language Models to generate music medicine. Ultimately, the output is intended to be used as a temporary relief between music therapy sessions with a board-certified therapist.
title Language Models for Music Medicine Generation
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2411.09080