X-Vectors with Multi-Scale Aggregation for Speaker Diarization.

Myungjong Kim Vijendra Raj Apsingekar Divya Neelagiri

Published in: CoRR (2021)

Keyphrases

speaker diarization
multiscale
speech recognition
image representation
audio stream
feature vectors
bayesian information criterion
image processing
machine learning
edge detection
broadcast news
speaker verification
image segmentation
speaker identification