Scansion-based Lyrics Generation

Yiwen Chen, Simone Teufel


Abstract
We aim to generate lyrics for Mandarin songs with a good match between the melody and the tonal contour of the lyrics. Our solution relies on mBart, treating lyrics generation as a translation problem, but rather than translating directly from the melody as is common, our novelty in this paper is that we generate from scansion as an intermediate contour representation that can fit a given melody. One of the advantages of our solution is that it does not require a parallel melody-lyrics dataset. We also present a thorough automatic evaluation of our system against competitors, using several new evaluation metrics. These measure intelligibility, fit to melody, and use proxies for quantifying creativity (variation to other songs created by the same system in different settings, semantic similarity to keywords given to the system, perplexity). When comparing different implementations of scansion to competitor systems, a varied picture emerges. Our best system outperforms all others in lyric-melody fit and is in the top group of systems for two of the creativity metrics (variation and perplexity), overshadowing two large language models (LLM) specialised to this task.
Anthology ID:
2024.lrec-main.1252
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
14370–14381
Language:
URL:
https://aclanthology.org/2024.lrec-main.1252
DOI:
Bibkey:
Cite (ACL):
Yiwen Chen and Simone Teufel. 2024. Scansion-based Lyrics Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 14370–14381, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Scansion-based Lyrics Generation (Chen & Teufel, LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.1252.pdf