update readme

Author: wszlong

README.md

@@ -20,13 +20,16 @@ Unified-modal speech-text pre-training for spoken language processing:
 
 > [**VALL-E X**](https://arxiv.org/abs/2303.03926) (```Arxiv 2023```): **Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling**
 
+> [**VioLA**](https://arxiv.org/abs/2305.16107) (```Arxiv 2023```): **VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation**
+
 <!-- Model introductions, evaluation results, and model inference instructions are located in the corresponding folders. The source code is [https://github.com/microsoft/SpeechT5/tree/main/ModelName]. -->
 
 
 ## Update
 
+- May, 2023: VioLA [**Arxiv**](https://arxiv.org/abs/2305.16107).
 - May, 2023: [**VATLM**](https://arxiv.org/abs/2211.11275) was accepted by IEEE Transactions on Multimedia.
-- March, 2023: VALL-E X [**Arxiv**](https://arxiv.org/abs/2303.03926) and [**Demo**](https://vallex-demo.github.io/).
+- March, 2023: VALL-E X [**Arxiv**](https://arxiv.org/abs/2303.03926) and [**Demo**](https://aka.ms/vallex).
 - February, 2023: [**Speech2S**](https://arxiv.org/abs/2210.17027) and [**Prosody-SpeechT5**](https://arxiv.org/abs/2211.11275) were accepted by ICASSP 2023.
 - [HuggingFace Integration] February, 2023: [**SpeechT5**](https://aclanthology.org/2022.acl-long.393/) models are on [**HuggingFace**](https://huggingface.co/blog/speecht5).
 - [Model Release] November, 2022: [**VATLM**](https://github.com/microsoft/SpeechT5/tree/main/VATLM) models are released.