Real-time speaker recognition system using multi-stream i-vectors for AI assistant.

Keunseok Cho Jaeyoung Roh Youngho Han Namhoon Kim Jaewon Lee

Published in: ICCE (2018)

Keyphrases

multi stream
real time
audio visual
audio visual speech recognition
artificial intelligence
multi modal
machine learning
hidden markov models
low level
speaker verification
image data
speech recognition
visual information
emotion recognition