Modeling structural topic transitions for automatic lyrics generation

Kento Watanabe, Yuichiroh Matsubayashi, Kentaro Inui, Masataka Goto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014
EditorsPrachya Boonkwan, Wirote Aroonmanakun, Thepchai Supnithi
PublisherFaculty of Pharmaceutical Sciences, Chulalongkorn University
Pages422-431
Number of pages10
ISBN (Electronic)9786165518871
Publication statusPublished - 2014 Jan 1
Event28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014 - Phuket, Thailand
Duration: 2014 Dec 122014 Dec 14

Publication series

NameProceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014

Other

Other28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014
CountryThailand
CityPhuket
Period14/12/1214/12/14

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science (miscellaneous)

Fingerprint Dive into the research topics of 'Modeling structural topic transitions for automatic lyrics generation'. Together they form a unique fingerprint.

  • Cite this

    Watanabe, K., Matsubayashi, Y., Inui, K., & Goto, M. (2014). Modeling structural topic transitions for automatic lyrics generation. In P. Boonkwan, W. Aroonmanakun, & T. Supnithi (Eds.), Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014 (pp. 422-431). (Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014). Faculty of Pharmaceutical Sciences, Chulalongkorn University.