PKSpell: Data-Driven Pitch Spelling and Key Signature Estimation - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

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.
Fichier principal
Vignette du fichier
PKSpell.pdf (419.13 Ko) Télécharger le fichier
Origin Publisher files allowed on an open archive

Dates and versions

hal-03300102 , version 1 (26-07-2021)

Identifiers

  • HAL Id : hal-03300102 , version 1

Cite

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⟩
174 View
89 Download

Share

Gmail Mastodon Facebook X LinkedIn More