Modeling Structural Topic Transitions for Automatic Lyrics Generation

By adopting recent advances in music creation technologies, such as digital audio workstations and singing voice synthesizers, people can now create songs in their personal computers. Computers can also assist in creating lyrics or generating them automatically, although this aspect has been less thoroughly researched and is limited to rhyme and meter. This study focuses on the structural relations in Japanese lyrics. We present novel generation models that capture the topic transitions between units peculiar to the lyrics, such as verse/chorus and line. These transitions are modeled by a Hidden Markov Model (HMM) for representing topics and topic transitions. To verify that our models generate contextsuitable lyrics, we evaluate the models using a log probability of lyrics generation and fill-in-the-blanks-type test. The results show that the language model is far more effective than HMM-based models, but the HMM-based approach successfully captures the inter-verse/chorus and inter-line relations. In the result of experimental evaluation, our approach captures the inter-verse/chorus and inter-line relations.