Combining Real-Time Extraction and Prediction of Musical Chord Progressions for Creative Applications

Recently, the field of musical co-creativity has gained some momentum. In this context, our goal is twofold: to develop an intelligent listening and predictive module of chord sequences, and to propose an adapted evaluation of the associated Music Information Retrieval (MIR) tasks that are the real-...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Tristan Carsault, Jérôme Nika, Philippe Esling, Gérard Assayag
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/21141a96168c4ada8599f768391dcb05
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:21141a96168c4ada8599f768391dcb05
record_format dspace
spelling oai:doaj.org-article:21141a96168c4ada8599f768391dcb052021-11-11T15:38:51ZCombining Real-Time Extraction and Prediction of Musical Chord Progressions for Creative Applications10.3390/electronics102126342079-9292https://doaj.org/article/21141a96168c4ada8599f768391dcb052021-10-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/21/2634https://doaj.org/toc/2079-9292Recently, the field of musical co-creativity has gained some momentum. In this context, our goal is twofold: to develop an intelligent listening and predictive module of chord sequences, and to propose an adapted evaluation of the associated Music Information Retrieval (MIR) tasks that are the real-time extraction of musical chord labels from a live audio stream and the prediction of a possible continuation of the extracted symbolic sequence. Indeed, this application case invites us to raise questions about the evaluation processes and methodology that are currently applied to chord-based MIR models. In this paper, we focus on <i>musical chords</i> since these mid-level features are frequently used to describe harmonic progressions in Western music. In the case of chords, there exists some strong inherent hierarchical and functional relationships. However, most of the research in the field of MIR focuses mainly on the performance of chord-based statistical models, without considering music-based evaluation or learning. Indeed, usual evaluations are based on a binary qualification of the classification outputs (right chord predicted versus wrong chord predicted). Therefore, we present a specifically-tailored chord analyser to measure the performances of chord-based models in terms of functional qualification of the classification outputs (by taking into account the harmonic function of the chords). Then, in order to introduce musical knowledge into the learning process for the automatic chord extraction task, we propose a specific musical distance for comparing predicted and labeled chords. Finally, we conduct investigations into the impact of including high-level metadata in chord sequence prediction learning (such as information on key or downbeat position). We show that a model can obtain better performances in terms of accuracy or perplexity, but output biased results. At the same time, a model with a lower accuracy score can output errors with more musical meaning. Therefore, performing a goal-oriented evaluation allows a better understanding of the results and a more adapted design of MIR models.Tristan CarsaultJérôme NikaPhilippe EslingGérard AssayagMDPI AGarticleinformaticsmusicchordslearningco-creativityco-improvisationElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2634, p 2634 (2021)
institution DOAJ
collection DOAJ
language EN
topic informatics
music
chords
learning
co-creativity
co-improvisation
Electronics
TK7800-8360
spellingShingle informatics
music
chords
learning
co-creativity
co-improvisation
Electronics
TK7800-8360
Tristan Carsault
Jérôme Nika
Philippe Esling
Gérard Assayag
Combining Real-Time Extraction and Prediction of Musical Chord Progressions for Creative Applications
description Recently, the field of musical co-creativity has gained some momentum. In this context, our goal is twofold: to develop an intelligent listening and predictive module of chord sequences, and to propose an adapted evaluation of the associated Music Information Retrieval (MIR) tasks that are the real-time extraction of musical chord labels from a live audio stream and the prediction of a possible continuation of the extracted symbolic sequence. Indeed, this application case invites us to raise questions about the evaluation processes and methodology that are currently applied to chord-based MIR models. In this paper, we focus on <i>musical chords</i> since these mid-level features are frequently used to describe harmonic progressions in Western music. In the case of chords, there exists some strong inherent hierarchical and functional relationships. However, most of the research in the field of MIR focuses mainly on the performance of chord-based statistical models, without considering music-based evaluation or learning. Indeed, usual evaluations are based on a binary qualification of the classification outputs (right chord predicted versus wrong chord predicted). Therefore, we present a specifically-tailored chord analyser to measure the performances of chord-based models in terms of functional qualification of the classification outputs (by taking into account the harmonic function of the chords). Then, in order to introduce musical knowledge into the learning process for the automatic chord extraction task, we propose a specific musical distance for comparing predicted and labeled chords. Finally, we conduct investigations into the impact of including high-level metadata in chord sequence prediction learning (such as information on key or downbeat position). We show that a model can obtain better performances in terms of accuracy or perplexity, but output biased results. At the same time, a model with a lower accuracy score can output errors with more musical meaning. Therefore, performing a goal-oriented evaluation allows a better understanding of the results and a more adapted design of MIR models.
format article
author Tristan Carsault
Jérôme Nika
Philippe Esling
Gérard Assayag
author_facet Tristan Carsault
Jérôme Nika
Philippe Esling
Gérard Assayag
author_sort Tristan Carsault
title Combining Real-Time Extraction and Prediction of Musical Chord Progressions for Creative Applications
title_short Combining Real-Time Extraction and Prediction of Musical Chord Progressions for Creative Applications
title_full Combining Real-Time Extraction and Prediction of Musical Chord Progressions for Creative Applications
title_fullStr Combining Real-Time Extraction and Prediction of Musical Chord Progressions for Creative Applications
title_full_unstemmed Combining Real-Time Extraction and Prediction of Musical Chord Progressions for Creative Applications
title_sort combining real-time extraction and prediction of musical chord progressions for creative applications
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/21141a96168c4ada8599f768391dcb05
work_keys_str_mv AT tristancarsault combiningrealtimeextractionandpredictionofmusicalchordprogressionsforcreativeapplications
AT jeromenika combiningrealtimeextractionandpredictionofmusicalchordprogressionsforcreativeapplications
AT philippeesling combiningrealtimeextractionandpredictionofmusicalchordprogressionsforcreativeapplications
AT gerardassayag combiningrealtimeextractionandpredictionofmusicalchordprogressionsforcreativeapplications
_version_ 1718434654134992896