Lipsynthesis incorporating audio-visual synchronisation

With the flourishing development of video-based information dissemination, audio and video synchronization is gradually becoming an important standard for measuring video quality.Deep synthesis technology has been entering the public's view in the international communication field, and lip-sync...

Full description

Saved in:
Bibliographic Details
Main Authors: Cong JIN, Jie WANG, Zichun GUO, Jing WANG
Format: Article
Language:zho
Published: POSTS&TELECOM PRESS Co., LTD 2023-09-01
Series:智能科学与技术学报
Subjects:
Online Access:http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202335
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850213713720639488
author Cong JIN
Jie WANG
Zichun GUO
Jing WANG
author_facet Cong JIN
Jie WANG
Zichun GUO
Jing WANG
author_sort Cong JIN
collection DOAJ
description With the flourishing development of video-based information dissemination, audio and video synchronization is gradually becoming an important standard for measuring video quality.Deep synthesis technology has been entering the public's view in the international communication field, and lip-sync technology integrating audio and video synchronization has attracted more and more attention.The existing lip-synthesis models are mainly based on lip-synthesis of static images, which are not effective for synthesis of dynamic videos, and most of them use English datasets for training which results in poor synthesis of Chinese Mandarin.To address these problems, this paper conducted optimization experiments on the Wav2Lip lip synthesis model in Chinese context based on its research foundation, and tested the effect of different routes of training models through multiple sets of experiments, which provided important reference values for the subsequent Wav2Lip series research.This study realized lip synthesis from speech-driven to text-driven, discussed the application of lip synthesis in multiple fields such as virtual digital human, and laid the foundation for the broader application and development of lip synthesis technology.
format Article
id doaj-art-564abe129b414c3fa466044de70ab33b
institution OA Journals
issn 2096-6652
language zho
publishDate 2023-09-01
publisher POSTS&TELECOM PRESS Co., LTD
record_format Article
series 智能科学与技术学报
spelling doaj-art-564abe129b414c3fa466044de70ab33b2025-08-20T02:09:05ZzhoPOSTS&TELECOM PRESS Co., LTD智能科学与技术学报2096-66522023-09-01539740542316534Lipsynthesis incorporating audio-visual synchronisationCong JINJie WANGZichun GUOJing WANGWith the flourishing development of video-based information dissemination, audio and video synchronization is gradually becoming an important standard for measuring video quality.Deep synthesis technology has been entering the public's view in the international communication field, and lip-sync technology integrating audio and video synchronization has attracted more and more attention.The existing lip-synthesis models are mainly based on lip-synthesis of static images, which are not effective for synthesis of dynamic videos, and most of them use English datasets for training which results in poor synthesis of Chinese Mandarin.To address these problems, this paper conducted optimization experiments on the Wav2Lip lip synthesis model in Chinese context based on its research foundation, and tested the effect of different routes of training models through multiple sets of experiments, which provided important reference values for the subsequent Wav2Lip series research.This study realized lip synthesis from speech-driven to text-driven, discussed the application of lip synthesis in multiple fields such as virtual digital human, and laid the foundation for the broader application and development of lip synthesis technology.http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202335lip generation;deep learning;artificial intelligence;computer visualization;synchronization of audio and video
spellingShingle Cong JIN
Jie WANG
Zichun GUO
Jing WANG
Lipsynthesis incorporating audio-visual synchronisation
智能科学与技术学报
lip generation;deep learning;artificial intelligence;computer visualization;synchronization of audio and video
title Lipsynthesis incorporating audio-visual synchronisation
title_full Lipsynthesis incorporating audio-visual synchronisation
title_fullStr Lipsynthesis incorporating audio-visual synchronisation
title_full_unstemmed Lipsynthesis incorporating audio-visual synchronisation
title_short Lipsynthesis incorporating audio-visual synchronisation
title_sort lipsynthesis incorporating audio visual synchronisation
topic lip generation;deep learning;artificial intelligence;computer visualization;synchronization of audio and video
url http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202335
work_keys_str_mv AT congjin lipsynthesisincorporatingaudiovisualsynchronisation
AT jiewang lipsynthesisincorporatingaudiovisualsynchronisation
AT zichunguo lipsynthesisincorporatingaudiovisualsynchronisation
AT jingwang lipsynthesisincorporatingaudiovisualsynchronisation