Papers by Kento Watanabe
A Melody-Conditioned Lyrics Language Model (N18-1)
Copied to clipboard
Kento Watanabe, Yuichiroh Matsubayashi, Satoru Fukayama, Masataka Goto, Kentaro Inui, Tomoyasu Nakano
| Challenge: | Existing models for lyrics generation are insufficient to capture relationship between lyrics and melody. |
| Approach: | They propose a data-driven language model that generates entire lyrics for a given melody. |
| Outcome: | The proposed model generates fluent lyrics while maintaining compatibility between lyrics and melodies. |
Unsupervised Learning of Style-sensitive Word Vectors (P18-2)
Copied to clipboard
| Challenge: | Existing studies on what is said and how it is said focus on stylistic variations . lack of objective definitions is a major difficulty in studying style . |
| Approach: | They propose to extend the continuous bag of words embedding model to learn style-sensitive word vectors using a wider context window. |
| Outcome: | The proposed extensions contribute to the acquisition of style-sensitive word embeddings. |
A Data-Driven Method for Analyzing and Quantifying Lyrics-Dance Motion Relationships (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have not explored the relationships between lyrics and dance motions . previous studies focused on synthesizing or retrieving dance motion from lyrics . |
| Approach: | They propose a method to detect parts of songs where meaningful relationships exist . they use clustering to transform lyrics and dance motions into symbols . |
| Outcome: | The proposed method outperforms existing methods on prose and non-dance dance motions. |