Update README.md

README.md

@@ -16,8 +16,9 @@ metrics:
 
 # X-UMX trained with the jaCappella corpus for vocal ensemble separation
 
-This model was trained by Tomohiko Nakamura using [the codebase](https://github.com/TomohikoNakamura/asteroid_jaCappella)).
-It was trained on the vocal ensemble separation task of [the jaCappella dataset](https://tomohikonakamura.github.io/jaCappella_corpus/).
+This model was trained by Tomohiko Nakamura using [the codebase](https://github.com/TomohikoNakamura/asteroid_jaCappella)).  
+It was trained on the vocal ensemble separation task of [the jaCappella dataset](https://tomohikonakamura.github.io/jaCappella_corpus/).  
+[The paper](https://doi.org/10.1109/ICASSP49357.2023.10095569) was published in ICASSP 2023 ([arXiv](https://arxiv.org/abs/2211.16028)).
 
 # License
 See [the jaCappella dataset page](https://tomohikonakamura.github.io/jaCappella_corpus/).