7 papers
Cross-Cultural Bias in Mel-Scale Representations: Evidence and Alternatives from Speech and Music
Shivam Chauhan, Ajay Pundhir
Modern audio systems universally employ mel-scale representations derived from 1940s Western psychoacoustic studies, potentially encoding cultural biases that create systematic per…
Covenant-72B: Pre-Training a 72B LLM with Trustless Peers Over-the-Internet
Joel Lidin, Amir Sarfi, Erfan Miahi +6
Recently, there has been increased interest in globally distributed training, which has the promise to both reduce training costs and democratize participation in building large-sc…
Who Gets Heard? Rethinking Fairness in AI for Music Systems
Atharva Mehta, Shivam Chauhan, Megha Sharma +5
In recent years, the music research community has examined risks of AI models for music, with generative AI models in particular, raised concerns about copyright, deepfakes, and tr…
Missing Melodies: AI Music Generation and its "Nearly" Complete Omission of the Global South
Atharva Mehta, Shivam Chauhan, Monojit Choudhury
Recent advances in generative AI have sparked renewed interest and expanded possibilities for music generation. However, the performance and versatility of these systems across mus…
Exploring Adapter Design Tradeoffs for Low Resource Music Generation
Atharva Mehta, Shivam Chauhan, Monojit Choudhury
Fine-tuning large-scale music generation models, such as MusicGen and Mustango, is a computationally expensive process, often requiring updates to billions of parameters and, there…
Music for All: Representational Bias and Cross-Cultural Adaptability of Music Generation Models
Atharva Mehta, Shivam Chauhan, Amirbek Djanibekov +3
The advent of Music-Language Models has greatly enhanced the automatic music generation capability of AI systems, but they are also limited in their coverage of the musical genres…