Design and Development of Music Composition System |
Author(s): |
Tanu Khandate , SDM College of Engineering and Technology, Dharwad, India; Deepti Ullikashi, SDM College of Engineering and Technology, Dharwad, India; Deepa Jadhav, SDM College of Engineering and Technology, Dharwad, India; Prof. J V Vadavi, SDM College of Engineering and Technology, Dharwad, India |
Keywords: |
RNN (Recurrent Neural Network), LSTM (Long Short Term Memory), MIDI (Musical Instrument Digital Inter- face), Char RNN Model, Music21 |
Abstract |
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, attempts at learning an entire musical form and using that knowledge to guide composition have been unsuccessful. The reason for this failure seems to be that RNNs cannot keep track of temporally distant events that indicate global music structure. Long Short-Term Memory (LSTM) has succeeded in similar domains where other RNNs have failed, such as timing and counting and CSL learning. In the current study we show that LSTM is also a good mechanism for learning to compose music. We compare this approach to previous attempts, with particular focus on issues of data representation. We present experimental results showing that LSTM successfully learns a form of piano music and is able to compose novel (and we believe pleasing) melodies in that style. Remarkably, once the network has found the relevant structure it does not drift from it: LSTM is able to play the piano with good timing and proper structure as long as one is willing to listen. |
Other Details |
Paper ID: IJSRDV8I30562 Published in: Volume : 8, Issue : 3 Publication Date: 01/06/2020 Page(s): 517-522 |
Article Preview |
|
|