Syllable Generation by Eliciting Knowledge of Recommended Song
Rohit R. Kumbhar, Amit K. Nerurkar, Bhavika P. Poojary, Parimal B. Pandhare · International Conference on Computing for Sustainable Global Development · 2019
The aim of this paper is to classify music according to its genre, predict the next song based on the current mood of the user and to play a small audio which describes the next song. The audio clip has information like artist name, album name, year of release and genre. This would make the system interactive. Here, content-based genre classification would be made by using Convolution Neural Network (CNN) and Recurrent Neural Network (RNN) in parallel. Based only on the recent history the next song is recommended so that it is according to the current mood of the user. The information such as name of the song, singer, music composer, album name, year of release is fetched from the dataset and played as an audio file before playing the song. By doing this, the user would get the information of the song in audio format. This would make the system user friendly as the user need not have to search about the song explicitly.