Can a machine win a Grammy? An evaluation of AI-generated song lyrics
Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021
Through lyrics, pitch, and rhythm, music is a natural way of expressing one's thoughts. As one of the essential music composition elements, lyrics' composition is complicated as it requires creativity and follows a particular rhythm pattern. In this work we design and train two neural network models for composing lyrics in three genres and propose scoring functions to select and evaluate the generated songs. We treat this problem as a text generation task, and optimize for features particular to song lyrics, including lyrics' quality, rhyme density, and sentiment ratio, for lyrics in different genres. The neural networks we have experimented with are generative adversarial network (GAN)-based transfer learning for a deep learning model and long short-term memory (LSTM)-based deep learning model. In addition to quantitative evaluation, we also conducted user studies, inviting 25 people to rate the generative songs selected by the scoring functions. Our findings show that the GAN-based models perform better than LSTM-based models and the scoring functions are useful in selecting good songs.
Evaluation metrics, Generative pretrained transformer, Long short-term memory, Lyrics generation, Recurrent neural networks, Unsupervised learning
Junlan Lu and Magdalini Eirinaki. "Can a machine win a Grammy? An evaluation of AI-generated song lyrics" Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021 (2021): 4896-4905. https://doi.org/10.1109/BigData52589.2021.9671431