Speaker clustering using vector representation with long-term feature for lecture speech recognition.

Chien-Lin Huang Chiori Hori Hideki Kashioka Bin Ma

Published in: ICASSP (2013)

Keyphrases

speech recognition
vector representation
document representation
language model
similarity measure
hidden markov models
pattern recognition
automatic speech recognition
speech signal
distance measure
feature selection
noisy environments
speaker identification
feature vectors
feature space
low level
multiscale