Filters








9 Hits in 2.4 sec

Harmtrace: Improving Harmonic Similarity Estimation Using Functional Harmony Analysis

W. Bas De Haas, José Pedro Magalhães, Remco C. Veltkamp, Frans Wiering
2011 Zenodo  
DISCUSSION The results show that using information about the function of a chord improves harmonic similarity.  ...  Hence, we can conclude that HARMTRACE significantly outperforms the other similarity measures, and that using the harmonic information obtained by our model improves similarity estimation on this dataset  ... 
doi:10.5281/zenodo.1417062 fatcat:752xvljc2zd3npgtseopmd5ffu

Automatic Functional Harmonic Analysis

W. Bas De Haas, José Pedro Magalhães, Frans Wiering, Remco C. Veltkamp
2013 Computer Music Journal  
In this article we present HarmTrace, a functional model of Western tonal harmony that builds on well-known theories of tonal harmony.  ...  For this, we use advanced functional programming techniques that are uniquely available in the Haskell programming language.  ...  For instance, in earlier work we applied HarmTrace to improve harmonic similarity estimation, using information about key that was available in the data .  ... 
doi:10.1162/comj_a_00209 fatcat:ap7n3s74kjc7lna2yg4kdssbqq

Improving Audio Chord Transcription By Exploiting Harmonic And Metric Knowledge

W. Bas De Haas, José Pedro Magalhães, Frans Wiering
2012 Zenodo  
For example, in automatic harmony analysis [8] , and similarity estimation [5] , chord labels are used as primary data representation.  ...  The chances that the HARMTRACE harmony model is over-fitting the used dataset are very low.  ... 
doi:10.5281/zenodo.1417540 fatcat:ewgb4duj3jgrdeghjcwihj4ngq

Functional modelling of musical harmony

José Pedro Magalhães, W. Bas de Haas
2011 Proceeding of the 16th ACM SIGPLAN international conference on Functional programming - ICFP '11  
As a detailed example, we show how our model can be used to improve content-based retrieval of jazz songs.  ...  Given a sequence of chord labels, the harmonic function of a chord in its tonal context is automatically derived.  ...  We thank Jurriaan Hage, Johan Jeuring, Andres Löh, Frans Wiering, and the anonymous reviewers for their helpful comments, and Doaitse Swierstra for his exhaustive technical support in using his parser  ... 
doi:10.1145/2034773.2034797 dblp:conf/icfp/MagalhaesH11 fatcat:khhatlzzw5ecvhtyxxxx4owi7u

A functional approach to automatic melody harmonisation

Hendrik Vincent Koops, José Pedro Magalhães, W. Bas de Haas
2013 Proceedings of the first ACM SIGPLAN workshop on Functional art, music, modeling & design - FARM '13  
In this work we describe FHARM, an automated system for melody harmonisation based on a functional model of harmony.  ...  Our system first generates multiple harmonically well-formed chord sequences for a given melody.  ...  Among other applications, these functional annotations can be used to improve the estimation of harmonic similarity of two chord sequences (De Haas et al. 2011) , and to improve chord recognition from  ... 
doi:10.1145/2505341.2505343 dblp:conf/icfp/KoopsMH13 fatcat:j2bpiz73azayjeoa2cvwyt4t64

Functional modelling of musical harmony

José Pedro Magalhães, W. Bas de Haas
2011 SIGPLAN notices  
As a detailed example, we show how our model can be used to improve content-based retrieval of jazz songs.  ...  Given a sequence of chord labels, the harmonic function of a chord in its tonal context is automatically derived.  ...  We thank Jurriaan Hage, Johan Jeuring, Andres Löh, Frans Wiering, and the anonymous reviewers for their helpful comments, and Doaitse Swierstra for his exhaustive technical support in using his parser  ... 
doi:10.1145/2034574.2034797 fatcat:3xlejfp3qncjvkkkb23db4l4wy

Leveraging Expert Domain Knowledge to Learn a Representation of Symbolic Music

Johanna Devaney
2017 Digital Humanities Conference  
This harmonic analysis will be performed by a hierarchical model of chord labels and phrases, which will function like a "language model" in speech recognition.  ...  Classification tasks include harmonic analysis or assessing the likelihood of a particular composer having composed a piece of unknown provenance, while similarity tasks include longitudinal studies over  ...  HarmTrace: Improving Harmonic similarity estimation using functional harmony analysis  ... 
dblp:conf/dihu/Devaney17a fatcat:hn4tjody7fdxndm6sirbsjkgie

Studying the effects of bass estimation for chord segmentation in pop-rock music

Urbez Capablo-Riazuelo, Perfecto Herrera
2014 Zenodo  
The results show a considerable improvement in the bass extraction task by using our approach and promising results in the bass transcription task.  ...  Bass information along with beat positions are then used to propose a novel type of audio segmentation for chromagram smoothing related to the chord estimation problem.  ...  It's is very interesting that it takes into account functional harmony, not only the name of chords. Actually, it performs a real harmonic analysis.  ... 
doi:10.5281/zenodo.3755371 fatcat:cbav4ax4xjc5xk46jz5xmjxgm4

In Search of Computer Music Analysis: Music Information Retrieval, Optimization, and Machine Learning from 2000-2016

Felicia Nafeeza Persaud, University, My, University, My
2018
My thesis aims to critically examine three methods in the current state of Computer Music Analysis. I will concentrate on Music Information Retrieval, Optimization, and Machine Learning.  ...  Preference Rules: Tonal-Class representation and Harmony HarmTrace can estimate the harmonic similarity, recognize chords, and automatically harmonize an input.  ...  This tool is useful for tonal works to separate data using harmonic similarity estimation, chord recognition, and automatic harmonization.  ... 
doi:10.20381/ruor-22264 fatcat:njkyjl6jurbjni46j4butxgwvq