paper and code

A proposed a novel AI framework to conduct real-time multi-speaker recognition without any prior registration or pre-training by learning the speaker identification on the fly. Considering the practical problem of online learning with episodically revealed rewards and introduced a solution based on semi-supervised and self-supervised learning methods in a web- based application
INTERSPEECH 2020 - "VoiceID on the fly: A Speaker Recognition System that Learns from Scratch"
https://www.youtube.com/watch?v=QqLnFS5_rCs
code https://github.com/doerlbh/MiniVox
paper https://arxiv.org/pdf/2006.04376.pdf
demo https://www.baihan.nyc/viz/VoiceID/