Speaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization.

Jenthe Thienpondt Kris Demuynck

Published in: Odyssey (2024)

Keyphrases

speaker diarization
weakly supervised
speech recognition
voice activity detection
topic models
object class
relation extraction
bayesian information criterion
feature selection
training set
semi supervised
audio visual
automatic speech recognition