Leveraging speaker diarization for meeting recognition from distant microphones.

Andreas Stolcke Gerald Friedland David Imseng

Published in: ICASSP (2010)

Keyphrases

speaker diarization
speech recognition
automatic speech recognition
broadcast news
audio stream

action recognition
object recognition
speech signal
feature extraction
pattern recognition

neural network
bayesian information criterion
human activities
speech activity detection
word error rate

speaker identification
unsupervised learning
language model
facial expressions
computer vision