Improving voice separation by better connecting contigs

Nicolas Guiomard-Kagan (1, 2) , Mathieu Giraud (3, 2) , Richard Groult (1, 2) , Florence Levé (3, 1, 2)

1 MIS - Modélisation, Information et Systèmes - UR UPJV 4290
2 Algomus
3 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189

Separating a polyphonic symbolic score into monophonic voices or streams helps to understand the music and may simplify further pattern matching. One of the best ways to compute this separation, as proposed by Chew and Wu in 2005, is to first identify contigs that are portions of the music score with a constant number of voices, then to progressively connect these contigs. This raises two questions: Which contigs should be connected first? And, how should these two contigs be connected? Here we propose to answer simultaneously these two questions by consid- ering a set of musical features that measures the quality of any connection. The coefficients weighting the features are optimized through a genetic algorithm. We benchmark the resulting connection policy on corpora containing fugues of the Well-Tempered Clavier by J. S. Bach as well as on string quartets, and we compare it against previously proposed policies. The contig connection is improved, particularly when one takes into account the whole content of voice fragments to assess the quality of their possible connection.

Mots clés: polyphony; voice separation; music information retrieval

Domaines: Musique, musicologie et arts de la scène; Son [cs.SD]

Nicolas Guiomard-Kagan, Mathieu Giraud, Richard Groult, Florence Levé. Improving voice separation by better connecting contigs. International Society for Music Information Retrieval Conference (ISMIR 2016), Aug 2016, New York, United States. ⟨hal-01331551⟩