Update README.md

README.md

@@ -48,13 +48,16 @@ This is due to the diverse nature of the AudioSet dataset used for pre-training,
 
 ## Citation
 
-If you use these pre-trained models in your work, please cite the following:
+If you use these pre-trained models in your work, please cite the following
+
 
 ```bib
 @article{ARCH,
   title={Benchmarking Representations for Speech, Music, and Acoustic Events},
-  author={La Quatra, Moreno and Koudounas, Alkis and Vaiani, Lorenzo and Baralis, Elena and Garza, Paolo and Cagliero, Luca, and Siniscalchi, Sabato Marco},
+  author={La Quatra, Moreno and Koudounas, Alkis and Vaiani, Lorenzo and Baralis, Elena and Garza, Paolo and Cagliero, Luca and Siniscalchi, Sabato Marco},
   year={2024},
   booktitle={2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)}, 
 }
-```
+```
+
+[arXiv version: arxiv.org/abs/2405.00934](arxiv.org/abs/2405.00934)