BYOL-A Is this independent of language?

nttcslab / byol-a

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

https://arxiv.org/abs/2103.06695

Other

204 stars 35 forks source link

BYOL-A Is this independent of language? #1

Closed parthplc closed 3 years ago

parthplc commented 3 years ago

Can we create vector representation using a pretrained model only for English or is it language Independent?

daisukelab commented 3 years ago

Hi @parthplc, my quick answer is language independent. But let me clarify some more. This research is for general purpose audio representation, not for speech recognition. So our encoder network is trained without putting an assumption of the type of the sound. I hope this answers your question.

daisukelab commented 3 years ago

Hi, I guess the question might be fulfilled, so let me close for now. Please feel free to reopen whenever you need.