update main page description (`4e68f75` in https://bitbucket.org/maum-system/cvpr22-demo-gradio)

docs/article.md

@@ -1,6 +1,17 @@
-[Youtube](https://youtu.be/F6h0s0M4vBI)
+## Why you learn a new language, when your model can learn it for you?
 
+### Abstract
 
+Recent studies in talking face generation have focused on building a train-once-use-everywhere model i.e. a model that will generalize from any source speech to any target identity. A number of works have already claimed this functionality and have added that their models will also generalize to any language. However, we show, using languages from different language families, that these models do not translate well when the training language and the testing language are sufficiently different. We reduce the scope of the problem to building a language-robust talking face generation system on seen identities i.e. the target identity is the same as the training identity. In this work, we introduce a talking face generation system that will generalize to different languages. We evaluate the efficacy of our system using a multilingual text-to-speech system. We also discuss the usage of joint text-to-speech system and the talking face generation system as a neural dubber system.
 
+[arXiv](https://arxiv.org/abs/2205.06421) (To be updated with CVPR Proceedings link)
 
-Recent studies in talking face generation have focused on building a train-once-use-everywhere model i.e. a model that will generalize from any source speech to any target identity. A number of works have already claimed this functionality and have added that their models will also generalize to any language. However, we show, using languages from different language families, that these models do not translate well when the training language and the testing language are sufficiently different. We reduce the scope of the problem to building a language-robust talking face generation system on seen identities i.e. the target identity is the same as the training identity. In this work, we introduce a talking face generation system that will generalize to different languages. We evaluate the efficacy of our system using a multilingual text-to-speech system. We also discuss the usage of joint text-to-speech system and the talking face generation system as a neural dubber system.
+### CVPR 2022 schedule
+
+This demonstration is mainly for CVPR 2022 virtual participants.  
+
+If you participate CVPR 2022 with passport(in-person) registration, you can meet our special demonstration in *Demo Area* from Tuesday to Thursday.
+
+- 21st, June (Tue) 10:00 ~ 13:30
+- 22nd, June (Wed) 10:00 ~ 12:30
+- 23rd, June (Thu) 10:00 ~ 12:00

docs/description.txt

@@ -1,4 +1,5 @@
-CVPR 2022 Demo Track (Round 1) #8 | 
 This system generates talking face video with corresponding text. 
 You can input text with one of four languages, which are Chinese, English, Japanese, and Korean. 
-If your text language and target language is different, it translates the sentence into target language with Google Translation API.
+If your text language and target language is different, it translates the sentence into target language with Google Translation API.
+
+(2022.06.05.) Due to the latency from HuggingFace Spaces and video rendering, it takes 15 ~ 30 seconds to get a video result.

docs/title.txt

@@ -1 +1 @@
-Talking Face Generation with Multilingual TTS
+Talking Face Generation with Multilingual TTS (CVPR 2022 Demo Track)