Self-Supervised Training of Speaker Encoder with Multi-Modal Diverse Positive Pairs.

Ruijie Tao Kong Aik Lee Rohan Kumar Das Ville Hautamäki Haizhou Li

Published in: CoRR (2022)

Keyphrases

multi modal
audio visual
multi modality
video search
pairwise
bit rate
image annotation
uni modal
training set
speech recognition
image registration
semantic concepts
speaker verification