diff --git a/README.md b/README.md
index 0ab0815bc68ad62e5ddd1a40150d2799c518e673..8381ae1b761166f9997d27aa3fbee50a73077754 100644
--- a/README.md
+++ b/README.md
@@ -108,3 +108,20 @@ Here is a short overview of the stages of the main script ```run.sh```:
   - **the parameter ```nclust``` in the script ```run.sh``` specifies the number of allowed clusters which should be modified depending on your task**
   - resulting ```*.png```-files (confusion matrices) are stored in ```exp_*/plots/kmenas/```
 
+## Citation
+
+If you use our code or data in your research, please cite our paper:
+
+> ["Linke, J., Kadar, M., Dosinszky, G., Mihajlik, P., Kubin, G., Schuppler, B. (2023) What do self-supervised speech representations encode? An analysis of languages, varieties, speaking styles and speakers. Proc. INTERSPEECH 2023, 5371-5375, doi: 10.21437/Interspeech.2023-951"]
+
+### BibTeX
+
+```bibtex
+@inproceedings{linke23_interspeech,
+  author={Julian Linke and Mate Kadar and Gergely Dosinszky and Peter Mihajlik and Gernot Kubin and Barbara Schuppler},
+  title={{What do self-supervised speech representations encode? An analysis of languages, varieties, speaking styles and speakers}},
+  year=2023,
+  booktitle={Proc. INTERSPEECH 2023},
+  pages={5371--5375},
+  doi={10.21437/Interspeech.2023-951}
+}
\ No newline at end of file