Implementation of lyric generation machine learning models in the Greek language for the genre of Éntekhno music. To accomplish this, we used three different Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN) approaches. The first method utilizes word-level bidirectional LSTMs, the second method expands on the first by learning the word embeddings on the initial layer of the network, while the last method is based on a char-level LSTM.
First two approaches based on code in enriqueav's repo.
Joint Work with with Athanasios Kefalas and Petros Tzallas
Please cite our paper if you use our work: https://link.springer.com/chapter/10.1007/978-3-030-49186-4_37