Towards deep interpretability (MuS-rover II): Learning hierarchical representations of tonal music

Haizi Yu, Lav R Varshney

Research output: Contribution to conferencePaper

Abstract

Music theory studies the regularity of patterns in music to capture concepts underlying music styles and composers' decisions. This paper continues the study of building automatic theorists (rovers) to learn and represent music concepts that lead to human interpretable knowledge and further lead to materials for educating people. Our previous work took a first step in algorithmic concept learning of tonal music, studying high-level representations (concepts) of symbolic music (scores) and extracting interpretable rules for composition. This paper further studies the representation hierarchy through the learning process, and supports adaptive 2D memory selection in the resulting language model. This leads to a deeper-level interpretability that expands from individual rules to a dynamic system of rules, making the entire rule learning process more cognitive. The outcome is a new rover, MUS-ROVER II, trained on Bach's chorales, which outputs customizable syllabi for learning compositional rules. We demonstrate comparable results to our music pedagogy, while also presenting the differences and variations. In addition, we point out the rover's potential usages in style recognition and synthesis, as well as applications beyond music.

Original languageEnglish (US)
StatePublished - Jan 1 2019
Event5th International Conference on Learning Representations, ICLR 2017 - Toulon, France
Duration: Apr 24 2017Apr 26 2017

Conference

Conference5th International Conference on Learning Representations, ICLR 2017
CountryFrance
CityToulon
Period4/24/174/26/17

Fingerprint

Dynamical systems
music
Data storage equipment
Chemical analysis
learning
learning process
composer
Music
Tonal
syllabus
regularity
language
Learning Process

ASJC Scopus subject areas

  • Education
  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Cite this

Yu, H., & Varshney, L. R. (2019). Towards deep interpretability (MuS-rover II): Learning hierarchical representations of tonal music. Paper presented at 5th International Conference on Learning Representations, ICLR 2017, Toulon, France.

Towards deep interpretability (MuS-rover II) : Learning hierarchical representations of tonal music. / Yu, Haizi; Varshney, Lav R.

2019. Paper presented at 5th International Conference on Learning Representations, ICLR 2017, Toulon, France.

Research output: Contribution to conferencePaper

Yu, H & Varshney, LR 2019, 'Towards deep interpretability (MuS-rover II): Learning hierarchical representations of tonal music' Paper presented at 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 4/24/17 - 4/26/17, .
Yu H, Varshney LR. Towards deep interpretability (MuS-rover II): Learning hierarchical representations of tonal music. 2019. Paper presented at 5th International Conference on Learning Representations, ICLR 2017, Toulon, France.
Yu, Haizi ; Varshney, Lav R. / Towards deep interpretability (MuS-rover II) : Learning hierarchical representations of tonal music. Paper presented at 5th International Conference on Learning Representations, ICLR 2017, Toulon, France.
@conference{bb37f93e1db24a1bbd7e29c8f9c3ba63,
title = "Towards deep interpretability (MuS-rover II): Learning hierarchical representations of tonal music",
abstract = "Music theory studies the regularity of patterns in music to capture concepts underlying music styles and composers' decisions. This paper continues the study of building automatic theorists (rovers) to learn and represent music concepts that lead to human interpretable knowledge and further lead to materials for educating people. Our previous work took a first step in algorithmic concept learning of tonal music, studying high-level representations (concepts) of symbolic music (scores) and extracting interpretable rules for composition. This paper further studies the representation hierarchy through the learning process, and supports adaptive 2D memory selection in the resulting language model. This leads to a deeper-level interpretability that expands from individual rules to a dynamic system of rules, making the entire rule learning process more cognitive. The outcome is a new rover, MUS-ROVER II, trained on Bach's chorales, which outputs customizable syllabi for learning compositional rules. We demonstrate comparable results to our music pedagogy, while also presenting the differences and variations. In addition, we point out the rover's potential usages in style recognition and synthesis, as well as applications beyond music.",
author = "Haizi Yu and Varshney, {Lav R}",
year = "2019",
month = "1",
day = "1",
language = "English (US)",
note = "5th International Conference on Learning Representations, ICLR 2017 ; Conference date: 24-04-2017 Through 26-04-2017",

}

TY - CONF

T1 - Towards deep interpretability (MuS-rover II)

T2 - Learning hierarchical representations of tonal music

AU - Yu, Haizi

AU - Varshney, Lav R

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Music theory studies the regularity of patterns in music to capture concepts underlying music styles and composers' decisions. This paper continues the study of building automatic theorists (rovers) to learn and represent music concepts that lead to human interpretable knowledge and further lead to materials for educating people. Our previous work took a first step in algorithmic concept learning of tonal music, studying high-level representations (concepts) of symbolic music (scores) and extracting interpretable rules for composition. This paper further studies the representation hierarchy through the learning process, and supports adaptive 2D memory selection in the resulting language model. This leads to a deeper-level interpretability that expands from individual rules to a dynamic system of rules, making the entire rule learning process more cognitive. The outcome is a new rover, MUS-ROVER II, trained on Bach's chorales, which outputs customizable syllabi for learning compositional rules. We demonstrate comparable results to our music pedagogy, while also presenting the differences and variations. In addition, we point out the rover's potential usages in style recognition and synthesis, as well as applications beyond music.

AB - Music theory studies the regularity of patterns in music to capture concepts underlying music styles and composers' decisions. This paper continues the study of building automatic theorists (rovers) to learn and represent music concepts that lead to human interpretable knowledge and further lead to materials for educating people. Our previous work took a first step in algorithmic concept learning of tonal music, studying high-level representations (concepts) of symbolic music (scores) and extracting interpretable rules for composition. This paper further studies the representation hierarchy through the learning process, and supports adaptive 2D memory selection in the resulting language model. This leads to a deeper-level interpretability that expands from individual rules to a dynamic system of rules, making the entire rule learning process more cognitive. The outcome is a new rover, MUS-ROVER II, trained on Bach's chorales, which outputs customizable syllabi for learning compositional rules. We demonstrate comparable results to our music pedagogy, while also presenting the differences and variations. In addition, we point out the rover's potential usages in style recognition and synthesis, as well as applications beyond music.

UR - http://www.scopus.com/inward/record.url?scp=85047013421&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047013421&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85047013421

ER -