Update readme to add diarization link

Updating readme to add link to diarization pipeline recipe and reference for diarization paper.

README.md

@@ -101,6 +101,15 @@ python train_speaker_embeddings.py hparams/train_ecapa_tdnn.yaml --data_folder=y
 
 You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/1-ahC1xeyPinAHp2oAohL-02smNWO41Cc?usp=sharing).
 
+# Speaker Diarization with ECAPA-TDNN Embeddings
+Note that, this trained ECAPA-TDNN model is used for speaker diarization task. A full diarization pipeline including boudary preparation using RTTM files, speaker embedding extraction, and backend spectral clustering for [AMI dataset](https://groups.inf.ed.ac.uk/ami/corpus/) can be found [here](https://github.com/speechbrain/speechbrain/tree/develop/recipes/AMI/Diarization).
+
+1. Run Inference for Diarization:
+```
+cd  recipes/AMI/Diarization
+python experiment.py hparams/ecapa_tdnn.yaml
+```
+
 ### Limitations
 The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
 
@@ -122,6 +131,18 @@ The SpeechBrain team does not provide any warranty on the performance achieved b
 }
 ```
 
+#### Referencing Speaker Diarization with ECAPA-TDNN
+```
+@inproceedings{dawalatabad21_interspeech,
+  author={Nauman Dawalatabad and Mirco Ravanelli and François Grondin and Jenthe Thienpondt and Brecht Desplanques and Hwidong Na},
+  title={{ECAPA-TDNN Embeddings for Speaker Diarization}},
+  year=2021,
+  booktitle={Proc. Interspeech 2021},
+  pages={3560--3564},
+  doi={10.21437/Interspeech.2021-941}
+}
+```
+
 # **Citing SpeechBrain**
 Please, cite SpeechBrain if you use it for your research or business.