Bias beyond Borders: Global Inequalities in AI-Generated Music
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916985550405632 |
|---|---|
| author | Solak, Ahmet Grötschla, Florian Lanzendörfer, Luca A. Wattenhofer, Roger |
| author_facet | Solak, Ahmet Grötschla, Florian Lanzendörfer, Luca A. Wattenhofer, Roger |
| contents | While recent years have seen remarkable progress in music generation models, research on their biases across countries, languages, cultures, and musical genres remains underexplored. This gap is compounded by the lack of datasets and benchmarks that capture the global diversity of music. To address these challenges, we introduce GlobalDISCO, a large-scale dataset consisting of 73k music tracks generated by state-of-the-art commercial generative music models, along with paired links to 93k reference tracks in LAION-DISCO-12M. The dataset spans 147 languages and includes musical style prompts extracted from MusicBrainz and Wikipedia. The dataset is globally balanced, representing musical styles from artists across 79 countries and five continents. Our evaluation reveals large disparities in music quality and alignment with reference music between high-resource and low-resource regions. Furthermore, we find marked differences in model performance between mainstream and geographically niche genres, including cases where models generate music for regional genres that more closely align with the distribution of mainstream styles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01963 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bias beyond Borders: Global Inequalities in AI-Generated Music Solak, Ahmet Grötschla, Florian Lanzendörfer, Luca A. Wattenhofer, Roger Sound Machine Learning While recent years have seen remarkable progress in music generation models, research on their biases across countries, languages, cultures, and musical genres remains underexplored. This gap is compounded by the lack of datasets and benchmarks that capture the global diversity of music. To address these challenges, we introduce GlobalDISCO, a large-scale dataset consisting of 73k music tracks generated by state-of-the-art commercial generative music models, along with paired links to 93k reference tracks in LAION-DISCO-12M. The dataset spans 147 languages and includes musical style prompts extracted from MusicBrainz and Wikipedia. The dataset is globally balanced, representing musical styles from artists across 79 countries and five continents. Our evaluation reveals large disparities in music quality and alignment with reference music between high-resource and low-resource regions. Furthermore, we find marked differences in model performance between mainstream and geographically niche genres, including cases where models generate music for regional genres that more closely align with the distribution of mainstream styles. |
| title | Bias beyond Borders: Global Inequalities in AI-Generated Music |
| topic | Sound Machine Learning |
| url | https://arxiv.org/abs/2510.01963 |