• Corpus ID: 237532324

BacHMMachine: An Interpretable and Scalable Model for Algorithmic Harmonization for Four-part Baroque Chorales

  title={BacHMMachine: An Interpretable and Scalable Model for Algorithmic Harmonization for Four-part Baroque Chorales},
  author={Yunyao Zhu and Stephen Hahn and Simon Mak and Yue Jiang and Cynthia Rudin},
Algorithmic harmonization – the automated harmonization of a musical piece given its melodic line – is a challenging problem that has garnered much interest from both music theorists and computer scientists. One genre of particular interest is the four-part Baroque chorales of J.S. Bach. Methods for algorithmic chorale harmonization typically adopt a blackbox, “data-driven” approach: they do not explicitly integrate principles from music theory but rely on a complex learning model trained with… 

Figures and Tables from this paper


DeepBach: a Steerable Model for Bach Chorales Generation
DeepBach, a graphical model aimed at modeling polyphonic music and specifically hymn-like pieces, is introduced, which is capable of generating highly convincing chorales in the style of Bach.
HARMONET: A Neural Net for Harmonizing Chorales in the Style of J. S. Bach
HARMONET, a system employing connectionist networks for music processing, is presented and is capable of producing four-part chorales in the style of J.S. Bach, given a one-part melody.
Counterpoint by Convolution
This model is an instance of orderless NADE, which allows more direct ancestral sampling, and finds that Gibbs sampling greatly improves sample quality, which is demonstrated to be due to some conditional distributions being poorly modeled.
Automatic Stylistic Composition of Bach Chorales with Deep LSTM
An AI system based upon LSTMs that was able to compose music like Johann Sebastian Bach was built, and analysis of the trained model provided evidence of neurons specializing without prior knowledge or explicit supervision to detect common music-theoretic concepts such as tonics, chords, and cadences.
Probabilistic harmonization with fixed intermediate chord constraints
The utilization of a well–studied probabilistic methodology, the hiddenMarkovmodel (HMM), in combination with additional constraints that incorporate intermediate fixed–chord constraints is discussed, and the constrained HMM (CHMM) is developed, harnessed with the novel general chord type (GCT) representation.
Music21: A Toolkit for Computer-Aided Musicology and Symbolic Music Data
This paper introduces the music21 system, demonstrating how to use it and the types of problems it is wellsuited toward advancing, and includes numerous examples of its power and flexibility.
The Complete Musician: An Integrated Approach to Tonal Theory, Analysis, and Listening
The Complete Musician brings together the analytical, aural, and tactile activities that comprise a tonal theory curriculum, The Complete Musicians, Second Edition, relies on a diverse ...
Harmonising Chorales by Probabilistic Inference
Using a probabilistic framework allows us to create a harmonisation system which learns from examples, and which can compose new harmonisations, and a quantitative comparison of the system's harmonisation performance against simpler models is made.
A Treatise on Harmony
Preface 1. The Stave 2. Harmony as derived from natural phenomena 3. Different positions of the tonic triad 4. General paradigm of harmonics 5. The minor mode deducible from nature 6. Natural origin
Artificial Intelligence: A Modern Approach
The long-anticipated revision of this #1 selling book offers the most comprehensive, state of the art introduction to the theory and practice of artificial intelligence for modern applications.