![]() ![]() The training data is limited as most songs are copyrighted, resulting in models that underfit the complicated cross-modal relationship between melody and lyrics. It is of significant practical interest and more challenging than unconstrained lyric generation as the music imposes additional constraints onto the lyrics. ![]() Publisher = "Association for Computational Linguistics",Ībstract = "Automatic melody-to-lyric generation is a task in which song lyrics are generated to go with a given melody. Cite (Informal): Unsupervised Melody-to-Lyrics Generation (Tian et al., ACL 2023) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: = "Unsupervised Melody-to-Lyrics Generation",īooktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", Association for Computational Linguistics. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9235–9254, Toronto, Canada. Unsupervised Melody-to-Lyrics Generation. Anthology ID: 2023.acl-long.513 Volume: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Month: July Year: 2023 Address: Toronto, Canada Venue: ACL SIG: Publisher: Association for Computational Linguistics Note: Pages: 9235–9254 Language: URL: DOI: 10.18653/v1/2023.acl-long.513 Bibkey: tian-etal-2023-unsupervised Cite (ACL): Yufei Tian, Anjali Narayan-Chen, Shereen Oraby, Alessandra Cervone, Gunnar Sigurdsson, Chenyang Tao, Wenbo Zhao, Tagyoung Chung, Jing Huang, and Nanyun Peng. Experimental results show that our model can generate high-quality lyrics that are more on-topic, singable, intelligible, and coherent than strong baselines, for example SongMASS, a SOTA model trained on a parallel dataset, with a 24% relative overall quality improvement based on human ratings. The two-step hierarchical design also enables content control via the lyric outline, a much-desired feature for democratizing collaborative song creation. The framework enables disentanglement of training (based purely on text) from inference (melody-guided text generation) to circumvent the shortage of parallel data.We leverage the segmentation and rhythm alignment between melody and lyrics to compile the given melody into decoding constraints as guidance during inference. Specifically, we design a hierarchical lyric generation framework that first generates a song outline and second the complete lyrics. In this work, we propose a method for generating high-quality lyrics without training on any aligned melody-lyric data. ![]() ![]() Released in 1976 on the album Black & Blue.Abstract Automatic melody-to-lyric generation is a task in which song lyrics are generated to go with a given melody.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |