Attentional networks for music generation

  title={Attentional networks for music generation},
  author={Gullapalli Keerti and A N Vaishnavi and Prerana Mukherjee and Aparna S Vidya and Gattineni Sai Sreenithya and Deeksha Nayab},
  journal={Multimedia Tools and Applications},
  pages={5179 - 5189}
Realistic music generation has always remained as a challenging problem as it may lack structure or rationality. In this work, we propose a deep learning based music generation method in order to produce old style music particularly JAZZ with rehashed melodic structures utilizing a Bi-directional Long Short Term Memory (Bi-LSTM) Neural Network with attention. Owing to the success in modelling long-term temporal dependencies in sequential data and its success in case of videos, Bi-LSTMs with… 

Toward Interactive Music Generation: A Position Paper

This work studies and analyzes the current advances in music generation using deep learning models through different criteria, and discusses the shortcomings and limitations of these models regarding interactivity and adaptability.

The Psychological Education Strategy of Music Generation and Creation by Generative Confrontation Network under Deep Learning

Both subjective and objective evaluations show that the generated music is more favored by the audience, indicating that the combination of deep learning and GAN has a great effect on music generation.

Folk melody generation based on CNN-BiGRU and Self-Attention

This paper proposes a melody generation network based on CNN-BiGRU and Self-Attention and shows that the prediction accuracy of the proposed model is improved and achieves improvement in other evaluation measures.

A Review of Intelligent Music Generation Systems

A comprehensive survey and analysis of recent intelligent music generation techniques, provide a critical discussion, explicitly identify their respective characteristics, and present them in a general table is conducted.

Pitch contours curve frequency domain fitting with vocabulary matching based music generation

The method proposed in this paper is the first to be used which uses the frequency domain characteristics of pitch contour curve to generate music melody with long-term structure controllable and has great development potential and application ability.



Bach in 2014: Music Composition with Recurrent Neural Network

It is shown that LSTM network learns the structure and characteristics of music pieces properly by demonstrating its ability to recreate music by predicting existing music using RProp outperforms Back propagation through time (BPTT).

A First Look at Music Composition using LSTM Recurrent Neural Networks

Long Short-Term Memory is shown to be able to play the blues with good timing and proper structure as long as one is willing to listen, and once the network has found the relevant structure it does not drift from it.

Interactive Music Generation with Positional Constraints using Anticipation-RNNs

This paper introduces a novel architecture called Anticipation-RNN which possesses the assets of the RNN-based generative models while allowing to enforce user-defined positional constraints and demonstrates its efficiency on the task of generating melodies satisfying positional constraints in the style of the soprano parts of the J.S. Bach chorale harmonizations.

Generating Polyphonic Music Using Tied Parallel Networks

A neural network architecture which enables prediction and composition of polyphonic music in a manner that preserves translation-invariance of the dataset and attains high performance at a musical prediction task and successfully creates note sequences which possess measure-level musical structure.

A Study on LSTM Networks for Polyphonic Music Sequence Modelling

This paper investigates the predictive power of simple LSTM networks for polyphonic MIDI sequences, using an empirical approach, and suggests that for AMT, a musically-relevant sample rate is crucial in order to model note transitions, beyond a simple smoothing effect.

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.

Creating melodies with evolving recurrent neural networks

  • C.-C.J. ChenR. Miikkulainen
  • Computer Science
    IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222)
  • 2001
This work observes that the model learns to generate melodies according to composition rules on tonality and rhythm with interesting variations and finds a neural network that maximizes the chance of generating good melodies.

End-to-end learning for music audio

  • S. DielemanB. Schrauwen
  • Computer Science
    2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2014
Although convolutional neural networks do not outperform a spectrogram-based approach, the networks are able to autonomously discover frequency decompositions from raw audio, as well as phase-and translation-invariant feature representations.

Attention is All you Need

A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely is proposed, which generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.