A melody-conditioned lyrics language model

Kento Watanabe, Yuichiroh Matsubayashi, Satoru Fukayama, Masataka Goto, Kentaro Inui, Tomoyasu Nakano

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

8 Citations (Scopus)

Abstract

This paper presents a novel, data-driven language model that produces entire lyrics for a given input melody. Previously proposed models for lyrics generation suffer from the inability of capturing the relationship between lyrics and melody partly due to the unavailability of lyrics-melody aligned data. In this study, we first propose a new practical method for creating a large collection of lyrics-melody aligned data and then create a collection of 1,000 lyrics-melody pairs augmented with precise syllable-note alignments and word/sentence/paragraph boundaries. We then provide a quantitative analysis of the correlation between word/sentence/paragraph boundaries in lyrics and melodies. We then propose an RNN-based lyrics language model conditioned on a featurized melody. Experimental results show that the proposed model generates fluent lyrics while maintaining the compatibility between boundaries of lyrics and melody structures.

Original languageEnglish
Title of host publicationLong Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages163-172
Number of pages10
ISBN (Electronic)9781948087278
Publication statusPublished - 2018
Event2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 - New Orleans, United States
Duration: 2018 Jun 12018 Jun 6

Publication series

NameNAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
Volume1

Conference

Conference2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018
CountryUnited States
CityNew Orleans
Period18/6/118/6/6

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics
  • Computer Science Applications

Fingerprint Dive into the research topics of 'A melody-conditioned lyrics language model'. Together they form a unique fingerprint.

Cite this