2020/09/30 by Vechtomova, Olga, Sahu, Gaurav, Kumar, Dhruv
#Computation and Language (cs.CL) #FOS: Computer and information sciences
paper · doi:10.48550/arxiv.2009.14375
We present a system for generating novel lyrics lines conditioned on music audio. A bimodal neural network model learns to generate lines conditioned on any given short audio clip. The model consists of a spectrogram variational autoencoder (VAE) and a text VAE. Both automatic and human evaluations demonstrate effectiveness of our model in generating lines that have an emotional impact matching a given audio clip. The system is intended to serve as a creativity tool for songwriters.