Voice And Stream: Perceptual And Computational Modeling Of Voice Separation

Cambouropoulos, Emilios

doi:10.1525/mp.2008.26.1.75

Cited by 36 publications

(34 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…11 Streams fall under the purview of auditory stream segregation and auditory scene analysis, concepts associated largely with the pioneering research of Albert S. Bregman (1990). There is a wide body of literature concerning this research area, a small sample from which are Bey and McAdams 2003;Cambouropoulos 2008;Deike et al 2004;Deutsch 2010;and Pressnitzer et al 2011. 12 a part .…”

Section: Invertible Counterpoint Within the Classical Stylementioning

confidence: 99%

The Theory and Practice of Integrating Invertible Counterpoint into Classical Theme-Types

Franck¹

2013

View full text Add to dashboard Cite

This essay investigates the use of invertible counterpoint within conventional theme-types encountered within Classical-style works. Whereas recent research has focused on how this contrapuntal technique provides a means of creating continuity, this article expands the purview by elucidating how it works in concert with theme-types, forms regulated by cadences (devices that arguably suppress continuity). A basic model provides the theoretical framework with which to analyze excerpts from a selection of works by Beethoven, Haydn, and Mozart. The analyses reveal that some theme-types are more successful than others at integrating invertible counterpoint into their formal design. Moreover, the analyses uncover the purpose of using invertible counterpoint within theme-types.Cet article examine l’utilisation du contrepoint réversible dans le cadre d’oeuvres thématiques conventionnelles de la tradition classique. Alors que de récentes recherches ont étudié comment cette technique contrapuntique peut créer une continuité, cet article contribue à cette question en montrant comment cette technique fonctionne de concert avec l’écriture thématique et les formes organisées par les cadences, et qui ont le propre d’interrompre la continuité. Un modèle de base sert de cadre théorique permettant l’analyse d’extraits tirés d’une sélection d’oeuvres de Haydn, Mozart et Beethoven. Les analyses montrent que certains types d’écriture thématique intègrent mieux que d’autres l’utilisation du contrepoint réversible dans leur organisation formelle. De plus, ces analyses mettent en lumière les divers rôles du contrepoint inversé dans les différentes formes thématiques

show abstract

Section: Invertible Counterpoint Within the Classical Stylementioning

confidence: 99%

The Theory and Practice of Integrating Invertible Counterpoint into Classical Theme-Types

Franck¹

2013

View full text Add to dashboard Cite

show abstract

“…Huron [8] presents a review of them, and derives a set of rules to be considered for writing music with perceptibly different voices. Based on this work, Cambouropoulos [4] separated a musical score into voices, using the following principles: "Synchronous Note" (notes starting at the same time are likely to be merged into a voice), "Temporal Continuity" and "Pitch Proximity" (the closer in time and pitch, it is more likely that consecutive notes belong to the same voice). Chew [5] considers slightly different principles, with a different view of musical "voice", not allowing multiple notes in a single stream, as opposed to [4].…”

Section: Multiple Pitch Estimation and Musical Stream Analysismentioning

confidence: 99%

Automatic melodic and structural analysis of music material for enriched concert related experiences

Bosch

2013

Proceedings of the 21st ACM International Conference on Multimedia

View full text Add to dashboard Cite

This PhD thesis proposal deals with the automatic analysis of musical audio, focusing on the estimation of the predominant melodic lines, which are used as a basis for extracting musical themes, and (along with other features) for structure recognition. The main focus is set on classical western music in large ensemble settings, which poses interesting research challenges to current state-of-the art algorithms. We will study the limitations of current approaches in this genre, and elaborate specific descriptors and methods, combining audio based analysis with further sources of knowledge and modalities. The creation of appropriate datasets will also be a main aspect, in order to properly evaluate the developed approaches. This work will be used to enrich musical concert related experiences, from music consumers to editors.

show abstract

“…Combining instrument assignment with this idea of using a music language model, it is natural to look towards the field of voice separation [25], which involves the separation of pitches into streams of notes, called voices, and is mainly addressed in the context of symbolic music processing. It is important to note that voice separation, while similar to our task of voice assignment, is indeed a distinct task.…”

Section: Introductionmentioning

confidence: 99%

“…There are many different definitions of what precisely constitutes a voice, both perceptually and musically, discussed more fully in [25]; however, for our purposes, a voice is quite simply defined as the notes sung by a single vocalist. Therefore, our interest in voice separation models lies with those that separate notes into strictly monophonic voices (i.e., those that do not allow for concurrent notes), rather than polyphonic voices as in [29].…”

Section: Introductionmentioning

confidence: 99%

Automatic Transcription of Polyphonic Vocal Music

et al. 2017

View full text Add to dashboard Cite

This paper presents a method for automatic music transcription applied to audio recordings of a cappella performances with multiple singers. We propose a system for multi-pitch detection and voice assignment that integrates an acoustic and a music language model. The acoustic model performs spectrogram decomposition, extending probabilistic latent component analysis (PLCA) using a six-dimensional dictionary with pre-extracted log-spectral templates. The music language model performs voice separation and assignment using hidden Markov models that apply musicological assumptions. By integrating the two models, the system is able to detect multiple concurrent pitches in polyphonic vocal music and assign each detected pitch to a specific voice type such as soprano, alto, tenor or bass (SATB). We compare our system against multiple baselines, achieving state-of-the-art results for both multi-pitch detection and voice assignment on a dataset of Bach chorales and another of barbershop quartets. We also present an additional evaluation of our system using varied pitch tolerance levels to investigate its performance at 20-cent pitch resolution.

show abstract

Voice And Stream: Perceptual And Computational Modeling Of Voice Separation

Cited by 36 publications

References 6 publications

The Theory and Practice of Integrating Invertible Counterpoint into Classical Theme-Types

The Theory and Practice of Integrating Invertible Counterpoint into Classical Theme-Types

Automatic melodic and structural analysis of music material for enriched concert related experiences

Automatic Transcription of Polyphonic Vocal Music

Contact Info

Product

Resources

About