HIGHLIGHTS
- who: Yingjin Song and collaborators from the Department of Information and Utrecht University, Netherlands University of Melbourne, Australia have published the research work: Modeling Emotion Dynamics in Song Lyrics with State Space Models, in the Journal: (JOURNAL)
- what: The authors propose a method to predict emotion dynamics in lyrics without song-level supervision. The experiments show that applying the method consistently improves the performance of sentence-level baselines without requiring any annotated songs making it ideal for limited training data scenarios. To show this, the authors propose Figure 1: The authors propose a hybrid_approach for . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.