A Prototypical Triplet Loss for Cover Detection

by   Guillaume Doras, et al.

Automatic cover detection – the task of finding in a audio dataset all covers of a query track – has long been a challenging theoretical problem in MIR community. It also became a practical need for music composers societies requiring to detect automatically if an audio excerpt embeds musical content belonging to their catalog. In a recent work, we addressed this problem with a convolutional neural network mapping each track's dominant melody to an embedding vector, and trained to minimize cover pairs distance in the embeddings space, while maximizing it for non-covers. We showed in particular that training this model with enough works having five or more covers yields state-of-the-art results. This however does not reflect the realistic use case, where music catalogs typically contain works with zero or at most one or two covers. We thus introduce here a new test set incorporating these constraints, and propose two contributions to improve our model's accuracy under these stricter conditions: we replace dominant melody with multi-pitch representation as input data, and describe a novel prototypical triplet loss designed to improve covers clustering. We show that these changes improve results significantly for two concrete use cases, large dataset lookup and live songs identification.


Cover Detection using Dominant Melody Embeddings

Automatic cover detection – the task of finding in an audio database all...

Pop2Piano : Pop Audio-based Piano Cover Generation

The piano cover of pop music is widely enjoyed by people. However, the g...

Characterization and exploitation of community structure in cover song networks

The use of community detection algorithms is explored within the framewo...

Early MFCC And HPCP Fusion for Robust Cover Song Identification

While most schemes for automatic cover song identification have focused ...

Investigating the efficacy of music version retrieval systems for setlist identification

The setlist identification (SLI) task addresses a music recognition use ...

Claraprint: a chord and melody based fingerprint for western classical music cover detection

Cover song detection has been an active field in the Music Information R...

On the entropy of coverable subshifts

A coloration w of Z^2 is said to be coverable if there exists a rectangu...

Please sign up or login with your details

Forgot password? Click here to reset