Skip to Main content Skip to Navigation
Conference papers

PKSpell: Data-Driven Pitch Spelling and Key Signature Estimation

Abstract : We present PKSpell: a data-driven approach for the joint estimation of pitch spelling and key signatures from MIDI files. Both elements are fundamental for the production of a full-fledged musical score and facilitate many MIR tasks such as harmonic analysis, section identification, melodic similarity, and search in a digital music library. We design a deep recurrent neural network model that only requires information readily available in all kinds of MIDI files, including performances, or other symbolic encodings. We release a model trained on the ASAP dataset. Our system can be used with these pre-trained parameters and is easy to integrate into a MIR pipeline. We also propose a data augmentation procedure that helps retraining on small datasets. PKSpell achieves strong key signature estimation performance on a challenging dataset. Most importantly, this model establishes a new state-of-the-art performance on the MuseData pitch spelling dataset without retraining.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03300102
Contributor : Francesco Foscarin <>
Submitted on : Monday, July 26, 2021 - 7:25:12 PM
Last modification on : Thursday, July 29, 2021 - 3:25:50 AM

Files

PKSpell.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-03300102, version 1

Collections

Citation

Francesco Foscarin, Nicolas Audebert, Raphaël Fournier-S'Niehotta. PKSpell: Data-Driven Pitch Spelling and Key Signature Estimation. International Society for Music Information Retrieval Conference (ISMIR), Nov 2021, Online, India. ⟨hal-03300102⟩

Share

Metrics

Record views

51

Files downloads

49