Update README.md

README.md

@@ -73,4 +73,28 @@ print(decode_wav([torchaudio.load('sample.wav')[0].squeeze()], model))
 # <|0.06| What are the many parts that make a machine learning system feel like it works so magically cheap? |5.86|>
 # <|5.68| Explletability factors important, so they tend to gear towards more simpler models with less parameters, but easier to explain, and on the other spectrum there are |15.86|>
 
-```
+```
+
+### Citation
+
+This repository uses the idea from the following paper. Please cite the paper if this model is used to help produce published results or is incorporated into other software.
+
+```text
+@INPROCEEDINGS{10446589,
+  author={Nguyen, Thai-Binh and Waibel, Alexander},
+  booktitle={ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
+  title={Synthetic Conversations Improve Multi-Talker ASR}, 
+  year={2024},
+  volume={},
+  number={},
+  pages={10461-10465},
+  keywords={Systematics;Error analysis;Knowledge based systems;Oral communication;Signal processing;Data models;Acoustics;multi-talker;asr;synthetic conversation},
+  doi={10.1109/ICASSP48485.2024.10446589}
+}
+```
+
+### Contact 
+
+nguyenvulebinh@gmail.com
+
+[![Follow](https://img.shields.io/twitter/follow/nguyenvulebinh?style=social)](https://twitter.com/intent/follow?screen_name=nguyenvulebinh)