My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
1–10 of 57 posts
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#2Co-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 free. Happy to go deep on the ML side.
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#3Co-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.
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#4will it help the barista in Starbucks get my name right finally?
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#5[flagged]
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#6Curious 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
#7[flagged]
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#8[flagged]
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#9[dead]
Re: My accent costs me 30 IQ points on Zoom. So we built an ML model to fix it
#10I would like to use such model but only if it really preserves my voice, otherwise people would understand its not me or I have to use it all the time.