Prompt-Based Music Discovery: A Prototype Using Source Separation And LLMs

Vansh Chugh

Keywords: Music Information Retrieval, Recommendation Systems, recommender, Software, Demo

TL;DR: Prototype for a method to look songs up using prompts like, "Find The Weeknd songs that use a trombone."

Abstract: We present the prototype of a music recommendation system enabling users to make specific requests using natural language prompts, such as "recommend hip-hop songs without drums but with guitar." Our approach combines audio source separation with large language model (LLM) query processing to bridge the gap between user intent and music discovery. The system uses Demucs 6-source separation to extract instrument presence information from 604 songs across 8 genres, stores metadata in a structured database, and employs Groq’s Llama-3.3-70B-Versatile model to convert natural language queries into SQL statements. While current capabilities focus on instrument presence detection, the system architecture supports future expansion to other MIR tasks. This prototype demonstrates the integration of music source separation (MSS) in recommendation systems.

Track: Demo Track

Confirmation: Demo Track: I confirm that I have followed the formatting guideline and included all author names and affiliations.

(Optional) Short Video Recording Link: https://youtu.be/w25tvlXW4pg

Submission Number: 42