Addressing the Fairness Issue of Large Music Models: A Blockchain Approach

Abstract

With the rapid development of AI, the integration of intelligent techniques into music has been booming rapidly in recent years. However, there is a rising concern about the fairness of large music models in generating culturally diverse musical compositions, emphasizing the need for inclusivity and equity in AI-generated music. By analyzing popular datasets such as the Million Song Dataset and the Lakh MIDI Dataset, we identify a significant under-representation of non-Western musical elements. To address this, we adapt existing models to incorporate non-Western scales, rhythms, and instruments. The adapted models demonstrate a substantial improvement in generating culturally diverse music. Additionally, we introduce a novel blockchain-based approach to ensure transparency and fairness in the data collection and model training processes. Blockchain technology enables secure, decentralized, and verifiable tracking of dataset contributions, ensuring that diverse cultural elements are adequately represented. Using AI-based synthetic listeners, we evaluate the impact of these adaptations on listener perception and engagement. Results indicate that music from the adapted models scores higher in terms of enjoyment, novelty, cultural resonance, and overall engagement compared to the original models. Our findings underscore the significance of cultural diversity in enhancing the user experience and promoting ethical AI practices. The study also discusses challenges, such as dataset limitations, model adaptation complexity, and the integration of blockchain technology. It suggests directions for future research to promote fairness and inclusivity in music AI further.