Multimodal Grounding for Sequence-to-sequence Speech Recognition.

Ozan Caglayan Ramon Sanabria Shruti Palaskar Loïc Barrault Florian Metze

Published in: ICASSP (2019)

Keyphrases

speech recognition
hidden markov models
language model
speech signal
pattern recognition
multi modal
speech processing
speech synthesis
acoustic models
speech recognition technology
machine learning
non stationary
automatic speech recognition
pseudorandom
speech recognizer
speech recognition errors