Towards Linking the Lakh and IMSLP Datasets
This addresses the challenge of linking large music datasets like Lakh and IMSLP for researchers and musicians, but it is incremental as it modifies an existing feature representation for hashing.
This paper tackles the problem of matching MIDI files to piano sheet music images in large databases, proposing a scalable cross-modal retrieval method that achieves a mean reciprocal rank of 0.84 and an average retrieval time of 25.4 seconds on a dataset of 5,000 scores.
This paper investigates the problem of matching a MIDI file against a large database of piano sheet music images. Previous sheet-audio and sheet-MIDI alignment approaches have primarily focused on a 1-to-1 alignment task, which is not a scalable solution for retrieval from large databases. We propose a method for scalable cross-modal retrieval that might be used to link the Lakh MIDI dataset with IMSLP sheet music data. Our approach is to modify a previously proposed feature representation called a symbolic bootleg score to be suitable for hashing. On a database of 5,000 piano scores containing 55,000 individual sheet music images, our system achieves a mean reciprocal rank of 0.84 and an average retrieval time of 25.4 seconds.