Beyond Genre: Diagnosing Bias in Music Embeddings Using Concept Activation Vectors
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908565395996672 |
|---|---|
| author | Gebhardt, Roman B. Kuhle, Arne Bektur, Eylül |
| author_facet | Gebhardt, Roman B. Kuhle, Arne Bektur, Eylül |
| contents | Music representation models are widely used for tasks such as tagging, retrieval, and music understanding. Yet, their potential to encode cultural bias remains underexplored. In this paper, we apply Concept Activation Vectors (CAVs) to investigate whether non-musical singer attributes - such as gender and language - influence genre representations in unintended ways. We analyze four state-of-the-art models (MERT, Whisper, MuQ, MuQ-MuLan) using the STraDa dataset, carefully balancing training sets to control for genre confounds. Our results reveal significant model-specific biases, aligning with disparities reported in MIR and music sociology. Furthermore, we propose a post-hoc debiasing strategy using concept vector manipulation, demonstrating its effectiveness in mitigating these biases. These findings highlight the need for bias-aware model design and show that conceptualized interpretability methods offer practical tools for diagnosing and mitigating representational bias in MIR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24482 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Genre: Diagnosing Bias in Music Embeddings Using Concept Activation Vectors Gebhardt, Roman B. Kuhle, Arne Bektur, Eylül Sound Audio and Speech Processing Music representation models are widely used for tasks such as tagging, retrieval, and music understanding. Yet, their potential to encode cultural bias remains underexplored. In this paper, we apply Concept Activation Vectors (CAVs) to investigate whether non-musical singer attributes - such as gender and language - influence genre representations in unintended ways. We analyze four state-of-the-art models (MERT, Whisper, MuQ, MuQ-MuLan) using the STraDa dataset, carefully balancing training sets to control for genre confounds. Our results reveal significant model-specific biases, aligning with disparities reported in MIR and music sociology. Furthermore, we propose a post-hoc debiasing strategy using concept vector manipulation, demonstrating its effectiveness in mitigating these biases. These findings highlight the need for bias-aware model design and show that conceptualized interpretability methods offer practical tools for diagnosing and mitigating representational bias in MIR. |
| title | Beyond Genre: Diagnosing Bias in Music Embeddings Using Concept Activation Vectors |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.24482 |