Abstract

The use of machine learning and deep learning to solve problems in literary arts has been a recent trend and gained much importance. Traditional issues like sound classification, Music source classification, and Music Autotagging have received enough attention from researchers. However, deep learning is receiving much importance in generating music. In this work, we have used Long Short Term Memory (LSTM) and Bidirectional Long Short Term Memory (BI-LSTM), which are classes of Recurrent Neural Network (RNN) to generate melodies. The direct use of these deep architectures may mimic the network's data samples without making meaning out of them. To justify the uniqueness of the generated music piece, We have used Dynamic Time Warping (DTW) technique, which measures the similarity between two temporal sequences, namely training music sample and generated music sample.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.