SynthPipe : AI based Human in the Loop Video Dubbing Pipeline

Anthony John Dsouza, Abigael Rachel Kumar, Akhil Koshy Wilson, Rupali Deshmukh
{"title":"SynthPipe : AI based Human in the Loop Video Dubbing Pipeline","authors":"Anthony John Dsouza, Abigael Rachel Kumar, Akhil Koshy Wilson, Rupali Deshmukh","doi":"10.1109/ICAECT54875.2022.9807853","DOIUrl":null,"url":null,"abstract":"Video content consumption via OTT platforms has been increasing over the years, with content creators worldwide creating exciting new content everyday. With this, regional content has skyrocketed in almost every language possible on platforms like YouTube, Twitch, etc. Such content may include daily soaps, educational or instructional videos, documentaries, movies, vlogs, etc which most of the time are in a language familiar to the creator. The same may not be the case for the viewer, who could be located anywhere and may not know the language of the creator. This creates a language barrier between the creator and viewer where every party involved suffers a loss - the creator loses on a global presence, the consumer loses on international content and both lose on a global community. To combat this, SynthPipe, a simple, modifiable, and efficient pipeline comprising of state-of-the-art techniques for video dubbing is proposed in this paper.","PeriodicalId":346658,"journal":{"name":"2022 Second International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT)","volume":"224 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 Second International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAECT54875.2022.9807853","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Video content consumption via OTT platforms has been increasing over the years, with content creators worldwide creating exciting new content everyday. With this, regional content has skyrocketed in almost every language possible on platforms like YouTube, Twitch, etc. Such content may include daily soaps, educational or instructional videos, documentaries, movies, vlogs, etc which most of the time are in a language familiar to the creator. The same may not be the case for the viewer, who could be located anywhere and may not know the language of the creator. This creates a language barrier between the creator and viewer where every party involved suffers a loss - the creator loses on a global presence, the consumer loses on international content and both lose on a global community. To combat this, SynthPipe, a simple, modifiable, and efficient pipeline comprising of state-of-the-art techniques for video dubbing is proposed in this paper.
SynthPipe:基于AI的人在循环视频配音管道
多年来,通过OTT平台的视频内容消费一直在增长,世界各地的内容创作者每天都在创作令人兴奋的新内容。因此,在YouTube、Twitch等平台上,区域性内容几乎以各种语言呈现。这些内容可能包括日常肥皂剧、教育或教学视频、纪录片、电影、视频日志等,大部分时间都是用创作者熟悉的语言制作的。对于观众来说,情况可能并非如此,他们可能身处任何地方,可能不知道创作者的语言。这就造成了创作者和观众之间的语言障碍,每一方都蒙受了损失——创作者失去了全球存在,消费者失去了国际内容,双方都失去了全球社区。为了解决这个问题,本文提出了SynthPipe,一个简单,可修改,高效的管道,包括最先进的视频配音技术。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信