[flagged]
My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
31–40 of 57 posts
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#32Nice to finally see this direction of accent conversion (that is on incoming calls) in the Krisp app. This is a very meaningful feature.
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#33[dead]
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#34Co-founder of Krisp here. 1.5B non-native English speakers in the workforce, 4x native — yet all comms infra is optimized for native accents. We spent 3 years building listener-side, on-device accent understanding. The hard parts: no parallel training data exists, the accent space is infinite, accent is entangled with voice identity, and it runs on CPU under 250ms latency. Built in Yerevan, Armenia. Beta is live and…
What do you think about the misuse potential (by scammers for example)? Aside from that, I like that this exists now.
This is for listener-side, not speaker-side.
So no misuse case here.
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#35[dead]
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#36Curious whether wav2vec-style embeddings played a role in your representation learning.
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#37[dead]
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#38Really cool to see accent adaptation in real time — curious about benchmarks and how well this handles messy, real Zoom calls
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#39Local CPU inference stands out. Careful optimization likely rivaled the modeling effort.
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#40Yeh, this would be helpful for the Singlish friends of mine out there!