Multimodal Speaker Diarization of Real-World Meetings Using D-Vectors With Spatial Features.

Wonjune Kang Brandon C. Roy Wesley Chow

Published in: ICASSP (2020)

Keyphrases

speaker diarization
spatial features
real world
speech recognition
spatial information
geometric properties
spatial objects
multi modal
spatial relationships
pattern discovery
bayesian information criterion
image processing
broadcast news
image classification
n gram
hyperspectral