NetScribed: A Deep Learning Approach for Machine-Based Melody Transcription of Audio Files

Francois Volschenk, Dustin van Der Haar

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Automatic Music Transcription (AMT) entails creating an algorithm that converts an acoustic signal from an audio file into the corresponding sheet music representation. This paper uses deep learning methods and models AMT as a translation problem, comparing the effectiveness of an instance-based translation approach using an MLP to a sequence-based approach using an RNN. The models were trained on the EsAc dataset and evaluated using MUSTER metrics. The results show that the instance-based model better classifies the correct pitch. However, the sequence-based approach outperforms the instance-based approach on all other aspects of the MUSTER metrics, producing a 98% accuracy.

Original languageEnglish
Title of host publicationApplied Informatics - 7th International Conference, ICAI 2024, Proceedings
EditorsHector Florez, Hernán Astudillo
PublisherSpringer Science and Business Media Deutschland GmbH
Pages105-118
Number of pages14
ISBN (Print)9783031751431
DOIs
Publication statusPublished - 2025
Event7th International Conference on Applied Informatics, ICAI 2024 - Vina del Mar, Chile
Duration: 24 Oct 202426 Oct 2024

Publication series

NameCommunications in Computer and Information Science
Volume2236 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference7th International Conference on Applied Informatics, ICAI 2024
Country/TerritoryChile
CityVina del Mar
Period24/10/2426/10/24

Keywords

  • Automatic Melody Transcription
  • Digital Signal Processing
  • Neural Networks

ASJC Scopus subject areas

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'NetScribed: A Deep Learning Approach for Machine-Based Melody Transcription of Audio Files'. Together they form a unique fingerprint.

Cite this