Polyphonic Music Composition with LSTM Neural Networks and Reinforcement Learning

2019-02-05 · Harish Kumar, Balaraman Ravindran

In the domain of algorithmic music composition, machine learning-driven systems eliminate the need for carefully hand-crafting rules for composition. In particular, the capability of recurrent neural networks to learn complex temporal patterns lends itself well to the musical domain. Promising results have been observed across a number of recent attempts at music composition using deep RNNs. These approaches generally aim at first training neural networks to reproduce subsequences drawn from existing songs. Subsequently, they are used to compose music either at the audio sample-level or at the note-level. We designed a representation that divides polyphonic music into a small number of monophonic streams. This representation greatly reduces the complexity of the problem and eliminates an exponential number of probably poor compositions. On top of our LSTM neural network that learnt musical sequences in this representation, we built an RL agent that learnt to find combinations of songs whose joint dominance produced pleasant compositions. We present Amadeus, an algorithmic music composition system that composes music that consists of intricate melodies, basic chords, and even occasional contrapuntal sequences.

📄 PDF Abstract BibTeX arXiv:1902.01973

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음

Tanh Activation 설명 없음

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Bach2Bach: Generating Music Using A Deep Reinforcement Learning Approach

2018-12-03 · Nikhil Kotecha

A model of music needs to have the ability to recall past details and have a clear, coherent understanding of musical structure. Detailed in the paper is a deep reinforcement learning architecture that predicts and gener…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

JamBot: Music Theory Aware Chord Based Generation of Polyphonic Music with LSTMs

2017-11-21 · Gino Brunner, Yuyi Wang, Roger Wattenhofer, Jonas Wiesendanger

We propose a novel approach for the generation of polyphonic music based on LSTMs. We generate music in two steps. First, a chord LSTM predicts a chord progression based on a chord embedding. A second LSTM then generates…

Generating Music using an LSTM Network

2018-04-18 · Nikhil Kotecha, Paul Young

A model of music needs to have the ability to recall past details and have a clear, coherent understanding of musical structure. Detailed in the paper is a neural network architecture that predicts and generates polyphon…

Polyphonic Music Composition: An Adversarial Inverse Reinforcement Learning Approach

2021-09-29 · Kelvin Xavier Munguia Velez, Von-Wun Soo

Most recent approaches to automatic music harmony composition adopt deep supervised learning to train a model using a set of human composed songs as training data. However, these approaches suffer from …

Q-Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Coupled Recurrent Models for Polyphonic Music Composition

2018-11-20 · John Thickstun, Zaid Harchaoui, Dean P. Foster, Sham M. Kakade

This paper introduces a novel recurrent model for music composition that is tailored to the structure of polyphonic music. We propose an efficient new conditional probabilistic factorization of musical scores, viewing a …

Time Series Analysis