[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]
2023-11: Warosu is now out of extended maintenance.

/vt/ - Virtual Youtubers


View post   

File: 154 KB, 1280x1000, Ejr6rJmVgAEaSfs.jpg [View same] [iqdb] [saucenao] [google]
47353972 No.47353972 [Reply] [Original]

This is just a thought that occured to me as I watched these two videos recently and while the system could be better, it's interesting how it uses a template of the person you want to be singing, and then matches that to a preexisting vocal performance.

https://www.youtube.com/watch?v=okSOpsIXn68

https://www.youtube.com/watch?v=yuZngMljVmo

it got me thinking about if we'd ever get to a point where streamers could be vocally translated in real time, using a similiar system for intonation, so that fans who don't speak their language could take part more.

A positive would be it potentially increasing the viewer base of the streamer, but a detriment and potential issue would be we may get less attempts at them speaking foreign languages (or perhaps lessen the likelihood of a viewer learning the language) and all the funny moments that has brought about, and if the streamer did decide to speak another language, would the translation system be able to detect that and not translate it? And with how sentence structures work in certain languages, would a AI system be able to keep the intonation of the spoken words intact? Do you even think it would be a idea worth pursuing or is even possible?

>>
Name
E-mail
Subject
Comment
Action