Live data from Hacker News

High-performance speech recognition with no supervision at all

ai.facebook.com

11–20 of 66 posts

Re: High-performance speech recognition with no supervision at all

#11

Hopefully they license it to Tesla so that my car stops misinterpreting 'call Jodie' as 'cool jodi'.

so close... you need to put your car in jabberish (jedi jibberish) command console which will then correctly understand "cool jodi" as "Cool Jedi" and enter mind control mode after which you'll only have to think of calling Jodie and the other phone will be ringing on speaker...

Re: High-performance speech recognition with no supervision at all

#12
post #8

Will Facebook license this tech out? I can't be the only one who's noticed Google's speech recognition has gotten significantly less accurate the last couple of years, probably the result of some cost-cutting strategy.

I wonder if it's less accurate for specific people, but more accurate generally. In other words speech recognition was more accurate in the beginning on english-speaking men, and maybe now it's better for women, kids, people with accents, other languages, etc... They train this on examples of speaking and maybe it's more broad now.

What in the world are you talking about?

Re: High-performance speech recognition with no supervision at all

#13
post #12
post #8

Earlier quoted context omitted.

I wonder if it's less accurate for specific people, but more accurate generally. In other words speech recognition was more accurate in the beginning on english-speaking men, and maybe now it's better for women, kids, people with accents, other languages, etc... They train this on examples of speaking and maybe it's more broad now.

What in the world are you talking about?

He's saying that it might not be getting worse due to a cost-cutting strategy, but rather an attempt to optimize the value for the most possible people.

Re: High-performance speech recognition with no supervision at all

#17
post #15

How does Facebook use speech recognition in its own products?

e.g., transcription of live streaming events?

Makes sense - transcribing speech from all uploaded video seems like it would be valuable for identifying interests and serving more personalized advertisements.

For example, in a video taken at the beach where someone says “wow that looks fun” (in any language) and there is a boat in the frame, you could serve them boat ads.

Re: High-performance speech recognition with no supervision at all

#20

How does Facebook use speech recognition in its own products?

A benevolent guess would be: It's probably related to their AR/VR effort. They are basically betting on AR/VR (incl Quest, Portal, etc) to be the next computing platform and voice input (also output) is a key user interaction model. IIRC, they are building a team to replicate Google Assistant and Siri.
Post reply on HN