InterSpeech 2020 - VoiceID on the fly: A Speaker Recognition System that Learns from Scratch
This is the free video InterSpeech 2020 - VoiceID on the fly: A Speaker Recognition System that Learns from Scratch that can be downloaded, played and edit with our RedcoolMedia movie maker MovieStudio free video editor online and AudioStudio free audio editor online
VIDEO DESCRIPTION:
Play, download and edit the free video InterSpeech 2020 - VoiceID on the fly: A Speaker Recognition System that Learns from Scratch.
Show & Tell Demo at InterSpeech 2020
"VoiceID on the fly: A Speaker Recognition System that Learns from Scratch"
Baihan Lin (UW) & Xinxin Zhang (UW)
Paper: arxiv.org/abs/2006.04376
Code: github.com/doerlbh/MiniVox
Demo: baihan.nyc/viz/VoiceID/
Abstract:
We 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. We considered the practical problem of online learning with episod- ically revealed rewards and introduced a solution based on semi-supervised and self-supervised learning methods in a web- based application at baihan.nyc/viz/VoiceID/.
Download, play and edit free videos and free audios from InterSpeech 2020 - VoiceID on the fly: A Speaker Recognition System that Learns from Scratch using RedcoolMedia.net web apps