Towards End-to-End Audio-Sheet-Music Retrieval
This addresses content-based musical retrieval for users needing cross-modal access, but it is incremental as it builds on existing DCCA methods.
The paper tackled the problem of retrieving sheet music images from audio queries and vice versa without symbolic representations, achieving promising results in initial experiments with monophonic music.
This paper demonstrates the feasibility of learning to retrieve short snippets of sheet music (images) when given a short query excerpt of music (audio) -- and vice versa --, without any symbolic representation of music or scores. This would be highly useful in many content-based musical retrieval scenarios. Our approach is based on Deep Canonical Correlation Analysis (DCCA) and learns correlated latent spaces allowing for cross-modality retrieval in both directions. Initial experiments with relatively simple monophonic music show promising results.