Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification.

Théo Lepage Réda Dehak

Published in: INTERSPEECH (2023)

Keyphrases

speech recognition
speaker verification
noisy environments
speaker recognition
language model
prosodic features
neural network
audio visual
multiscale
multi modal
emotion recognition
information retrieval
multimedia
training set
probabilistic model
language identification