updated.

README.md

@@ -134,7 +134,7 @@ The NeMo toolkit [3] was used for training the models for over several hundred e
 
 ### Datasets
 
-All the models in this collection are trained on AISHELL2 comprising of Mandarin speech:
+All the models in this collection are trained on AISHELL2 [4] comprising of Mandarin speech:
 
 ## Performance
 
@@ -163,6 +163,7 @@ Check out [Riva live demo](https://developer.nvidia.com/riva#demos).
 [1] [Conformer: Convolution-augmented Transformer for Speech Recognition](https://arxiv.org/abs/2005.08100)
 [2] [Google Sentencepiece Tokenizer](https://github.com/google/sentencepiece)
 [3] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)
+[4] [AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale](https://arxiv.org/abs/1808.10583)
 
 ## Licence