Harmonising Chorales by Probabilistic Inference

By Moray Allan, Christopher K. I. Williams. 2004

191 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

Citations in the corpus

Music Transformer: Generating Music with Long-Term Structure (2018, methodology): “B ACH C HORALES J.S. Bach chorales is a canonical dataset used for evaluating generative models for music 3 (e.g., Allan & Williams, 2005; Boulanger-Lewandowski et al., 2012; Liang, 2016; Hadjeres et al., 2016; Huang et al., 2017).”
LSTM: A Search Space Odyssey (2015, background): “JSB Chorales is a collection of 382 four-part harmonized chorales by J. S. Bach (Allan & Williams, 2005), consisting of 202 chorales in major keys and 180 chorals in minor keys.”
Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription (2012, methodology): “JSB chorales refers to the entire corpus of 382 four-part harmonized chorales by J. S. Bach with the split of Allan & Williams (2005).”
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling (2018, background): “JSB Chorales (Allan & Williams, 2005) is a polyphonic music dataset consisting of the entire corpus of 382 four-part harmonized chorales by J. S. Bach.”
LakhNES: Improving Multi-instrumental Music Generation with Cross-domain Pre-training (2019, background): “Other research focuses on the multi-instrumental setting and seeks to provide systems which can harmonize with human-composed material [17–20].”
Deep Learning Techniques for Music Generation - A Survey (2017, methodology): “Bach [1]; the MuseData library, an electronic classical music library from CCARH in Stanford [71]; the Nottingham database, a collection of 1,200 folk tunes in ABC notation [49]; and the Classical piano MIDI database [96].”
Counterpoint by Convolution (2019, methodology): “While the literature features many variants of this dataset [1, 4, 14, 27], we report results on that used by [4].”
DeepBach: a Steerable Model for Bach Chorales Generation (2016, methodology): “A similar approach is adopted in (Allan & Williams, 2005), but uses Hidden Markov Models (HMMs) instead of neural networks.”
Convolutional Sequence Modeling Revisited (2018, methodology): “JSB Chorales: JSB Chorales dataset (Allan & Williams, 2005) is a polyphonic music dataset consisting of the entire corpus of 382 four-part harmonized chorales by J. S. Bach.”
Style Imitation and Chord Invention in Polyphonic Music with Exponential Families (2016, methodology): “[14] and [1] describe a HMM approach trained on an annotated corpus.”
A Functional Taxonomy of Music Generation Systems (2017, methodology): “The size of the search space is relevant to the number of states in a hidden Markov models [Allan and Williams 2005], the number of nodes in a neural network [Hild et al. 1992], and the length of the chromosome in a genetic algorithm [McIn-tyre 1994].”
An Improved Relative Self-Attention Mechanism for Transformer with Application to Music Generation (2018, background): “Bach Chorales is a canonical dataset used for evaluating generative models for music [1, 3, 7, 11, 17].”