keyboard_arrow_up
An Efficient AI Music Generation mobile platform Based on Machine Learning and ANN Network

Authors

Jiacheng Dai1 and Yu Sun2, 1China, 2California State Polytechnic University, USA

Abstract

The aim of this paper is to provide a solution to the growing need for fresh music to use in media, as adding music can greatly enhance the media’s atmosphere and the viewers’ experience [6]. Our solution to this issue was the creation of a mobile application named MFly that can output music using the sentiment from an inputted message. To test the effectiveness of this new music-generating method, an experiment was conducted in which twenty-three participants inputted a message with a positive and negative sentiment each and recorded whether each outputted musical piece accurately represented the sentiment from the message [7]. A post-experiment survey was also provided to each of the participants to gauge the convenience and practicality of the application. The results indicated that MFly was largely successful at conveying messages into appropriately fitting music. However, the practicality of the application could use some work, as generating music based on the sentiment does not always seem to match up with the original inputted message's sentiment, especially with messages that have a negative sentiment. Furthermore, feedback from participants indicated that the application could still improve with the addition of more features, such as the ability to save the generated music for later use.

Keywords

Machine Learning, AI, Mobile application.

Full Text  Volume 12, Number 17