HIGHLIGHTS
- who: Tunu00e7 Yu0131lmaz from the University of Potsdam, Potsdam, Germany have published the article: Song authorship attribution: a lyrics and rhyme based approach, in the Journal: (JOURNAL)
- what: The authors propose CNN models for on this lyric data set to use structural information included in the similarly to image classification. The authors attempt to discover idiosyncratic features and consequently author and genre associations by working with variants of CNN architectures that have been successfully used in other text classification domains. Apart from character and sub-word level embeddings that indicate positional and lexical information, the . . .
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.