Login / Signup
Combining multiple end-to-end speech recognition models based on density ratio approach.
Keigo Hojo
Daiki Mori
Yukoh Wakabayashi
Kengo Ohta
Atsunori Ogawa
Norihide Kitaoka
Published in:
APSIPA ASC (2023)
Keyphrases
</>
end to end
speech recognition
combining multiple
pattern recognition
hidden markov models
congestion control
speech signal
probabilistic model
language model
speech recognizer
acoustic models
computer vision
optical flow
speech recognition systems
least squares