Update README.md

README.md

@@ -30,7 +30,8 @@ The SI-SNR estimator is trained with a recordings from the WHAMR! and LibriMix d
 
 This model is released together with the REAL-M dataset for source separation on in-the-wild speech mixtures. 
 
-The class necessary to perform inference has not yet been yet to the SpeechBrain, but will be merged to the develop branch soon!
+The REAL-M dataset can downloaded from [this link](https://sourceseparationresearch.com/static/REAL-M-v0.1.0.tar.gz).
+The paper for the REAL-M dataset can be found on [this arxiv link](https://arxiv.org/pdf/2110.10812.pdf). 
 
 ## Install SpeechBrain
 
@@ -86,16 +87,18 @@ The SpeechBrain team does not provide any warranty on the performance achieved b
 }
 ```
 
+#### Referencing REAL-M
 
-#### Referencing SepFormer
 ```bibtex
-@inproceedings{subakan2021attention,
-      title={Attention is All You Need in Speech Separation}, 
-      author={Cem Subakan and Mirco Ravanelli and Samuele Cornell and Mirko Bronzi and Jianyuan Zhong},
+@misc{subakan2021realm,
+      title={REAL-M: Towards Speech Separation on Real Mixtures}, 
+      author={Cem Subakan and Mirco Ravanelli and Samuele Cornell and François Grondin},
       year={2021},
-      booktitle={ICASSP 2021}
+      eprint={2110.10812},
+      archivePrefix={arXiv},
+      primaryClass={eess.AS}
 }
-```
+``` 
 
 # **About SpeechBrain**
 - Website: https://speechbrain.github.io/