Update README.md

README.md

@@ -20,7 +20,8 @@ List of available models:
 - <mark>en_us_cmuarctic_pt_univenet.addon</mark> - en-US TTS trained on all 18
   [CMU Arctic](http://festvox.org/cmu_arctic/) voices. This includes
   examples of absolutely dashing accents, with "slp" voice being my
-  personal absolute favorite. Model consists of Parallel Tacotron
+  personal absolute favorite. Model consists of
+  [Parallel Tacotron](https://arxiv.org/abs/2010.11439)
   and pre-trained [Univnet](https://github.com/mindslab-ai/univnet).
   Model produces 24khz audio, although original dataset is unfortunately
   16khz, so high frequencies are empty :(