FreshJam: Suggesting Continuations of Melodic Fragments in a Specific Style
نویسندگان
چکیده
Imagine that a budding composer suffers from writer’s block partway through devising a melody. A system called FreshJam is demonstrated, which offers a solution to this problem in the form of an interactive composition assistant; an algorithm that analyzes the notes composed so far, makes a comparison with an indexed corpus of existing music, and suggests a possible next note by choosing randomly among continuations of matched melody fragments. We provide a demonstration of FreshJam as an aid in stylistic composition, and of its potential to be more iterative than existing composition assistants such as PG Music’s Band in a Box or Microsoft’s Songsmith. There are many algorithms that, with one button click, generate entire melodies or passages of music in the style of another composer or period (Conklin and Witten 1995; Cope 2005; Pearce and Wiggins 2007). These one-click algorithms can be used to test theories of musical style, but are of little honest use to students of stylistic composition. This seems unfortunate, as some of the algorithms work by generating one note/chord at a time, and so are eminently suited to form the basis of a system for interactive music composition. Below we describe such a system, called FreshJam, in which users are able to request continuations to melodic fragments in a specific style. Compared with other models for compositional continuation (Cope 1997; Maxwell et al. 2012), the principles behind FreshJam are simple and few, and there is an argument for considering and evaluating simpler models before developing more complex alternatives. The term FreshJam refers to the piano-roll, web-based interface in which users compose a melody, and the term composition assistant refers to the functionality by which the user can request a continuation for their melody fragment (see www.projectfreshjam.com for a video demonstration). Figure 1 shows a schematic for the composition assistant. At the start of the flow diagram, the user has composed a fragment of n melody notes. Unsure how to proceed, they request a continuation from the composition assistant. If the user has not already selected a composer/style for the source of continuations, they are prompted to do so at this Copyright c © 2012, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. FreshJam! State transition tables (user"s choice)! Melody of!
منابع مشابه
Pii: S0010-0277(00)00068-8
This article is a study of melodic expectancy in North Sami yoiks, a style of music quite distinct from Western tonal music. Three different approaches were taken. The ®rst approach was a statistical style analysis of tones in a representative corpus of 18 yoiks. The analysis determined the relative frequencies of tone onsets and twoand three-tone transitions. It also identi®ed style characteri...
متن کامل"If You Have to Ask, You'll Never Know": Effects of Specialised Stylistic Expertise on Predictive Processing of Music
Musical expertise entails meticulous stylistic specialisation and enculturation. Even so, research on musical training effects has focused on generalised comparisons between musicians and non-musicians, and cross-cultural work addressing specialised expertise has traded cultural specificity and sensitivity for other methodological limitations. This study aimed to experimentally dissociate the e...
متن کاملExpectancy in melody: tests of children and adults.
Melodic expectancies among children and adults were examined. In Experiment 1, adults, 11-year-olds, and 8-year-olds rated how well individual test tones continued fragments of melodies. In Experiment 2, 11-, 8-, and 5-year-olds sang continuations to 2-tone stimuli. Response patterns were analyzed using 2 models of melodic expectancy. Despite having fewer predictor variables, the 2-factor model...
متن کاملMusical Style Identification Using Self-Organising Maps
In this paper the capability of using self-organising neural maps (SOM) as music style classifiers from symbolic specifications of musical fragments is studied. From MIDI file sources, the monophonic melody track is extracted and cut into fragments of equal length. From these sequences, melodic, harmonic, and rhythmic numerical descriptors are computed and presented to the SOM. Their performanc...
متن کاملFeature-driven recognition of music styles
In this paper the capability of using self-organising neural maps (SOM) as music style classifiers of musical fragments is studied. From MIDI files, the monophonic melody track is extracted and cut into fragments of equal length. From these sequences, melodic, harmonic, and rhythmic numerical descriptors are computed and presented to the SOM. Their performance is analysed in terms of separabili...
متن کامل