Speaker Diarization Using Convolutional Neural Network for Statistics Accumulation Refinement.

Zbynek Zajíc Marek Hrúz Ludek Müller

Published in: INTERSPEECH (2017)

Keyphrases

convolutional neural network
speaker diarization
face detection
speech recognition
audio stream
neural network
object detection
visual information
face recognition
pairwise
hidden markov models
broadcast news
speaker verification