arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.00418cs.CVcs.AIcs.LGcs.MMcs.SD
收藏

自动面对面翻译

Towards Automatic Face-to-Face Translation

IIIT Hyderabad(印度国际信息技术学院海得拉巴分校);IIT Kanpur(印度理工学院坎普尔分校)

Prajwal K R, Rudrabha Mukhopadhyay, Jerin Philip, Abhishek Jha, Vinay Namboodiri, C. V. Jawahar

摘要:

鉴于自动机器翻译系统的最新突破,我们提出了一种新的方法,我们称之为“面对面翻译”。随着今天的数字通信变得越来越可视化,我们认为,有必要的系统,可以自动翻译成目标语言B与现实的嘴唇同步的一个人说的语言A的视频。在这项工作中,我们为这个问题创建了一个自动管道,并展示了它对多个现实世界应用程序的影响。首先,我们通过整合语音和语言的多个现有模块来构建一个语音到语音的翻译系统。然后,我们转向“面对面翻译”,通过将一个新的视觉模块,LipGAN从翻译的音频生成逼真的说话脸。LipGAN在标准LRW测试集上的定量评估表明,它在所有标准指标上都显着优于现有方法。我们还对我们的面对面翻译管道进行了多次人工评估,并表明它可以显着改善跨语言消费和交互多模态内容的整体用户体验。代码、模型和演示视频都是公开的。演示视频:https://www.youtube.com/watch? v=aHG6Oei8jF0代码和型号:https://github.com/Rudrabha/LipGAN

英文摘要:

In light of the recent breakthroughs in automatic machine translation systems, we propose a novel approach that we term as "Face-to-Face Translation". As today's digital communication becomes increasingly visual, we argue that there is a need for systems that can automatically translate a video of a person speaking in language A into a target language B with realistic lip synchronization. In this work, we create an automatic pipeline for this problem and demonstrate its impact on multiple real-world applications. First, we build a working speech-to-speech translation system by bringing together multiple existing modules from speech and language. We then move towards "Face-to-Face Translation" by incorporating a novel visual module, LipGAN for generating realistic talking faces from the translated audio. Quantitative evaluation of LipGAN on the standard LRW test set shows that it significantly outperforms existing approaches across all standard metrics. We also subject our Face-to-Face Translation pipeline, to multiple human evaluations and show that it can significantly improve the overall user experience for consuming and interacting with multimodal content across languages. Code, models and demo video are made publicly available. Demo video: https://www.youtube.com/watch?v=aHG6Oei8jF0 Code and models: https://github.com/Rudrabha/LipGAN

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑