Applying Source Separation to Music

Pardo, Bryan; Duan, Zhiyao; Richard, Gaël

doi:10.1002/9781119279860.ch16

Cited by 5 publications

(2 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Previous research has established close relations between ensemble coordination at the level of sounds and body motion [ 6 , 7 , 23 ] and our previous work found correspondences between overall synchrony and audio event density [ 44 ]. Although signal processing techniques exist for separating sound sources from mixed recordings [ 93 , 94 ], and recent work has assessed ensemble synchrony directly from the overall group output using recurrence quantification analysis [ 95 ], the types of recordings we analysed are not well-suited for these techniques. Sound source separation can be problematic to the extent that instrumental timbres are similar (as is the case of the string sounds in our dataset).…”

Section: Discussionmentioning

confidence: 99%

Leadership dynamics in musical groups: Quantifying effects of musical structure on directionality of influence in concert performance videos

Sabharwal,

Breaden,

Volpe

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Music ensemble performance provides an ecologically valid context for investigating leadership dynamics in small group interactions. Musical texture, specifically the relative salience of simultaneously sounding ensemble parts, is a feature that can potentially alter leadership dynamics by introducing hierarchical relationships between individual parts. The present study extended previous work on quantifying interpersonal coupling in musical ensembles by examining the relationship between musical texture and leader-follower relations, operationalised as directionality of influence between co-performers’ body motion in concert video recordings. It was hypothesised that the directionality of influence, indexed by Granger Causality, would be greater for ‘homophonic’ textures with a clear distinction between melody and accompaniment parts than for ‘polyphonic’ textures with less distinction between melody and accompaniment. This hypothesis was tested by using pose estimation algorithms to track instrumentalists’ body movements in a string quartet and a clarinet quintet, and then applying Granger Causality analysis to their head motion to estimate directional influence between instrumentalist pairs for sections of the pieces that varied in texture. It was found that Granger Causality values were generally higher (indicating greater directionality of influence) for homophonic than polyphonic textures. Furthermore, considering melody and accompaniment instrument roles revealed more evidence for the melody instrument influencing accompanying instruments than vice versa, plus a high degree of directionality among accompanying instruments, in homophonic textures. These observed patterns of directional information flow in co-performer body motion are consistent with changing leader-follower relations depending on hierarchical relations between ensemble parts in terms of the relative salience of melodic material in the musical texture. The finding that automatic pose estimation can detect modulations of leadership dynamics in standard video recordings under naturalistic performance conditions has implications for investigating interpersonal coordination in large-scale music video datasets representing different cultural traditions, and for exploring nonverbal communication in group activities more generally.

show abstract

Section: Discussionmentioning

confidence: 99%

Leadership dynamics in musical groups: Quantifying effects of musical structure on directionality of influence in concert performance videos

Sabharwal,

Breaden,

Volpe

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…O recurso levantado foi a biblioteca Demucs, disponibilizada por parte da equipe de pesquisa Meta AI [18]. Dentre outras opções levantadas, essa foi a de mais fácil uso.…”

Section: Componente De Isolamento De Instrumentounclassified

Comparação De Padrões Melódicos Para Recuperação Musical

NECYK AGNER CALDAS

View full text Add to dashboard Cite

Este projeto se propõe a explorar métodos de comparação melódica monofônica para construção de ferramenta de auxílio à identificação de padrões musicais, com foco no processo de composição. Discute-se técnicas para resolver o problema de recuperação baseada em conteúdo melódico, no qual o usuário recupera informações sobre determinada obra musical através de uma interpretação, cantada ou tocada, de seus fragmentos melódicos. Para tal, levanta-se ferramentas já existentes para viabilizar a construção do protótipo que implementa os métodos discutidos.Palavras-chave reconhecimento de melodias monofônicas, extração de padrões melódicos, recuperação baseada em conteúdo, música.

show abstract

Deep Learning for Audio and Music

Peeters

Richard

2012

Multi-Faceted Deep Learning

View full text Add to dashboard Cite

Applying Source Separation to Music

Cited by 5 publications

References 67 publications

Leadership dynamics in musical groups: Quantifying effects of musical structure on directionality of influence in concert performance videos

Leadership dynamics in musical groups: Quantifying effects of musical structure on directionality of influence in concert performance videos

Comparação De Padrões Melódicos Para Recuperação Musical

Deep Learning for Audio and Music

Contact Info

Product

Resources

About