The Spheres Dataset: Multitrack Orchestral Recordings for Music Source Separation and Information Retrieval
This dataset solves the problem of limited training data for researchers and developers working on machine learning tasks like source separation and information retrieval in the classical music domain, representing an incremental contribution by providing a new resource.
The paper introduces The Spheres dataset, a collection of multitrack orchestral recordings designed to address the lack of data for music source separation in classical music, providing over one hour of recordings with isolated stems and acoustic characterizations for supervised training and benchmarking.
This paper introduces The Spheres dataset, multitrack orchestral recordings designed to advance machine learning research in music source separation and related MIR tasks within the classical music domain. The dataset is composed of over one hour recordings of musical pieces performed by the Colibrì Ensemble at The Spheres recording studio, capturing two canonical works - Tchaikovsky's Romeo and Juliet and Mozart's Symphony No. 40 - along with chromatic scales and solo excerpts for each instrument. The recording setup employed 23 microphones, including close spot, main, and ambient microphones, enabling the creation of realistic stereo mixes with controlled bleeding and providing isolated stems for supervised training of source separation models. In addition, room impulse responses were estimated for each instrument position, offering valuable acoustic characterization of the recording space. We present the dataset structure, acoustic analysis, and baseline evaluations using X-UMX based models for orchestral family separation and microphone debleeding. Results highlight both the potential and the challenges of source separation in complex orchestral scenarios, underscoring the dataset's value for benchmarking and for exploring new approaches to separation, localization, dereverberation, and immersive rendering of classical music.