State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions.

Kyu J. Han Ramon Prieto Kaixing Wu Tao Ma

Published in: CoRR (2019)

Keyphrases

multi stream
audio visual
audio visual speech recognition
hidden markov models
multi modal
high level
pattern recognition
visual information
emotion recognition
data sets
high dimensional
image data
image classification