Speaker segmentation using deep speaker vectors for fast speaker change scenarios.

Renyu Wang Mingliang Gu Lantian Li Mingxing Xu Thomas Fang Zheng

Published in: ICASSP (2017)

Keyphrases

audio visual
speaker verification
speech recognition
speaker recognition
speaker diarization
speaker identification
image segmentation
ground truth
image processing
multimedia
face recognition
color images
automatic speech recognition
segmentation errors
prosodic features
speaker dependent