Deep Rapping: Character Level Neural Models for Automated Rap Lyrics Composition
Aaron Carl T. Fernandez1, Ken Jon M. Tarnate2, Madhavi Devaraj3
1Aaron Carl T. Fernandez, Mapua University, Manila, Philippines.
2Ken Jon M. Tarnate, Mapua University, Manila, Philippines.
3Dr. Madhavi Devaraj, Mapua University, Manila, Philippines.
Manuscript received on 10 December 2018 | Revised Manuscript received on 17 December 2018 | Manuscript Published on 30 December 2018 | PP: 306-311 | Volume-8 Issue- 2S December 2018 | Retrieval Number: BS2651128218/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: “Dope”, “Twerk”, “YOLO”, these are just some of the words that originated from rap music which made into the Oxford dictionary. Rap lyrics break the traditional structure of English, making use of shorten and invented words to create rhythmic lines and inject informality, humor, and attitude in the music. In this paper, we attack this domain on a computational perspective, by implementing deep learning models that could forge rap lyrics through unsupervised character prediction. Our work employed novel recurrent neural networks for the task at hand and showed that these can emulate human creativity in rap lyrics composition based on qualitative analysis, rhyme density score, and Turing test performed on computer science students.
Keywords: Gated Recurrent Unit; Long Short-Term Memory; Natural Language Generation; Recurrent Neural Networks.
Scope of the Article: Community Information Systems