Music transcription modelling and composition using deep learning

Abstract

We apply deep learning methods, specifically long short-term memory (LSTM) networks, to music transcription modelling and composition. We build and train LSTM networks using approximately 23,000 music transcriptions expressed with a high-level vocabulary (ABC notation), and use them to generate new transcriptions. Our practical aim is to create music transcription models useful in particular contexts of music composition. We present results from three perspectives: 1) at the population level, comparing descriptive statistics of the set of training transcriptions and generated transcriptions; 2) at the individual level, examining how a generated transcription reflects the conventions of a music practice in the training transcriptions (Celtic folk); 3) at the application level, using the system for idea generation in music composition. We make our datasets, software and sound examples open and available: \url{https://github.com/IraKorshunova/folk-rnn}.

arXiv comment16 pages, 4 figures, contribution to 1st Conference on Computer Simulation of Musical Creativity

References in corpus (4)

• Sequence to Sequence Learning with Neural Networks
• On the difficulty of training Recurrent Neural Networks
• Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
• Comparing Probabilistic Models for Melodic Sequences

Cited by in corpus (9)

• 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
• Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey
• Adaptive Music Composition for Games
• Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control
• AAG-Stega: Automatic Audio Generation-based Steganography
• Vector Quantized Contrastive Predictive Coding for Template-based Music Generation
• Improving Automatic Jazz Melody Generation by Transfer Learning Techniques
• Conjugate Distribution Laws in Cultural Evolution via Statistical Learning