Deep Speaker Embeddings Based Online Diarization.

Anastasia Avdeeva Sergey Novoselov

Published in: SPECOM (2022)

Keyphrases

speaker diarization
online learning
low dimensional
speaker identification
high dimensional
audio visual
dimensionality reduction
euclidean space
vector space
maximum likelihood
deep learning
manifold learning
high dimensional data
database
feature vectors
digital libraries
website
artificial intelligence