Text-based LSTM networks for Automatic Music Composition

Abstract

In this paper, we introduce new methods and discuss results of text-based LSTM (Long Short-Term Memory) networks for automatic music composition. The proposed network is designed to learn relationships within text documents that represent chord progressions and drum tracks in two case studies. In the experiments, word-RNNs (Recurrent Neural Networks) show good results for both cases, while character-based RNNs (char-RNNs) only succeed to learn chord progressions. The proposed system can be used for fully automatic composition or as semi-automatic systems that help humans to compose music by controlling a diversity parameter of the model.

Accepted in the 1st Conference on Computer Simulation of Musical Creativity, 2016

References in corpus (1)

• Recurrent Neural Network Regularization

Cited by in corpus (19)

• Predicting Process Behaviour using Deep Learning
• Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators
• A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions
• Imposing higher-level Structure in Polyphonic Music Generation using Convolutional Restricted Boltzmann Machines and Constraints
• Feature Engineering and Forecasting via Derivative-free Optimization and Ensemble of Sequence-to-sequence Networks with Applications in Renewable Energy
• TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method
• Talking Drums: Generating drum grooves with neural networks
• Can GAN originate new electronic dance music genres? -- Generating novel rhythm patterns using GAN with Genre Ambiguity Loss
• Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhyme
• Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin
• DeepDrum: An Adaptive Conditional Neural Network
• Artificial Neural Networks Jamming on the Beat
• Everybody Compose: Deep Beats To Music
• LSTM Networks for Music Generation
• Identity Recognition in Intelligent Cars with Behavioral Data and LSTM-ResNet Classifier
• M6(GPT)3: Generating Multitrack Modifiable Multi-Minute MIDI Music from Text using Genetic algorithms, Probabilistic methods and GPT Models in any Progression and Time Signature
• Multi-Step Chord Sequence Prediction Based on Aggregated Multi-Scale Encoder-Decoder Network
• Modeling Musical Structure with Artificial Neural Networks
• Differential Music: Automated Music Generation Using LSTM Networks with Representation Based on Melodic and Harmonic Intervals