• Corpus ID: 3226639

Computer Assisted Composition with Recurrent Neural Networks

  title={Computer Assisted Composition with Recurrent Neural Networks},
  author={Christian J. Walder and Dongwoo Kim},
Sequence modeling with neural networks has lead to powerful models of symbolic music data. We address the problem of exploiting these models to reach creative musical goals, by combining with human input. To this end we generalise previous work, which sampled Markovian sequence models under the constraint that the sequence belong to the language of a given finite state machine provided by the human. We consider more expressive non-Markov models, thereby requiring approximate sampling which we… 
Computer Assisted Composition in Continuous Time
This work introduces a simple, novel, and efficient particle filter scheme, applicable to general continuous time point processes, and demonstrates that in comparison with a more traditional beam search baseline, the particle filter exhibits superior statistical properties and yields more agreeable results in an extensive human listening test experiment.
Anticipation-RNN: enforcing unary constraints in sequence generation, with application to interactive music generation
This article introduces a novel architecture called anticipation-RNN which possesses the assets of the RNN-based generative models while allowing to enforce user-defined unary constraints and demonstrates its efficiency on the task of generating melodies satisfying unary constraint in the style of the soprano parts of the J.S. Bach chorale harmonizations.
Neural Dynamic Programming for Musical Self Similarity
A neural sequence model designed specifically for symbolic music, based on a learned edit distance mechanism which generalises a classic recursion from computer sci- ence, leading to a neural dynamic program.
Generation of Melodies for the Lost Chant of the Mozarabic Rite
Prior to the establishment of the Roman rite with its Gregorian chant, in the Iberian Peninsula and Southern France the Mozarabic rite, with its own tradition of chant, was dominant from the sixth
Research on Emotional Music Reconstruction Method Based on DBN-GRU
In the process of music therapy, in order to solve the problems of short music segments with poor emotional adjustment effect and poor emotional perception of patients, this paper proposes an
Sequence Generation Using Unwords
  • D. Conklin
  • Computer Science
    PKDD/ECML Workshops
  • 2019
The two concepts of statistical models and unexpectedly absent words can be combined for sequence generation, by sampling from a statistical model while avoiding generation of any unwords.
Scaffold-constrained molecular generation
This work builds on the well-known SMILES-based Recurrent Neural Network (RNN) generative model, with a modified sampling procedure, to achieve scaffold-constrained generation, and directly benefit from the associated reinforcement learning methods, allowing to design molecules optimized for different properties while exploring only the relevant chemical space.


Modelling Symbolic Music: Beyond the Piano Roll
A representation which reduces polyphonic music to a univariate categorical sequence is introduced, which is able to apply state of the art natural language processing techniques, namely the long short-term memory sequence model.
Neural Network Music Composition by Prediction: Exploring the Benefits of Psychoacoustic Constraints and Multi-scale Processing
  • M. Mozer
  • Computer Science, Engineering
    Connect. Sci.
  • 1994
An extension of this transition-table approach is described, using a recurrent autopredictive connectionist network called CONCERT, which is trained on a set of pieces with the aim of extracting stylistic regularities and incorporation of psychologically grounded representations of pitch, duration and harmonic structure.
Algorithmic Composition of Melodies with Deep Recurrent Neural Networks
This work investigates how artificial neural networks can be trained on a large corpus of melodies and turned into automated composers able to generate new melodies coherent with the style they have been trained on.
A First Look at Music Composition using LSTM Recurrent Neural Networks
In general music composed by recurrent neural networks (RNNs) suffers from a lack of global structure. Though networks can learn note-by-note transition probabilities and even reproduce phrases,
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.
Algorithmic Composition: Paradigms of Automated Music Generation
This is the first book to provide a detailed overview of prominent procedures of algorithmic composition in a pragmatic way rather than by treating formalizable aspects in single works.
Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
A probabilistic model based on distribution estimators conditioned on a recurrent neural network that is able to discover temporal dependencies in high-dimensional sequences that outperforms many traditional models of polyphonic music on a variety of realistic datasets is introduced.
Generative Music Evaluation: Why do We Limit to ‘Human’?
Objective evaluation of aesthetic subjective judgements is, by very definition, tricky business. This may be the reason many generative music systems merely skip the evaluation part entirely. Typical
Folk music style modelling by recurrent neural networks with long short term memory units
We demonstrate two generative models created by training a recurrent neural network (RNN) with three hidden layers of long short-term memory (LSTM) units. This extends past work in numerous
Enforcing Meter in Finite-Length Markov Sequences
This article introduces meter, a constraint that ensures a sequence is 1) Markovian with regards to a given corpus and 2) follows metrical rules expressed as cumulative cost functions, and proposes a domain consistency algorithm whose complexity is pseudo-polynomial.