Technology

142 readers

103 users here now

Share interesting Technology news and links.

Rules:

No paywalled sites at all.
News articles has to be recent, not older than 2 weeks (14 days).
No videos.
Post only direct links.

To encourage more original sources and keep this space commercial free as much as I could, the following websites are Blacklisted:

NBC.
CNBC.
NY Magazine.
Substack.
Tom's Hardware.
ZDNet.
TechSpot.
Ars Technica.
The Verge.
Engadget.
TechCrunch.
Gizmodo.

Encouraged:

Archive links in the body of the post.
Linking to the direct source, instead of linking to an article talking about the source.

founded 4 weeks ago

MODERATORS

Pro@programming.dev

AI headphones translate multiple speakers at once, cloning their voices in 3D sound (www.washington.edu)

submitted 3 weeks ago* (last edited 3 weeks ago) by Pro@programming.dev to c/Technology@programming.dev

1 comments fedilink hide all child comments

Chen and a team of UW researchers have designed a headphone system that translates several speakers at once, while preserving the direction and qualities of people’s voices. The team built the system, called Spatial Speech Translation, with off-the-shelf noise-cancelling headphones fitted with microphones. The team’s algorithms separate out the different speakers in a space and follow them as they move, translate their speech and play it back with a 2-4 second delay.

you are viewing a single comment's thread
view the rest of the comments

[–] supernicepojo@lemmy.world 1 points 3 weeks ago* (last edited 3 weeks ago)

Im happy they finally found Paul Allen, cant wait to see his business card.

For more information, contact the researchers babelfish@cs.washington.edu

Multiple voices, cloned, then translated. 2-4 seconds is a really long pause for realworld conversation though. Cool tech making big leaps here.