Cross-Modal Knowledge Distillation for Audiovisual Speech Recognition.

L. Ashok Kumar Dhanaraj Karthika Renuka V. Dineshraja Fatima Abdul Jabbar

Published in: FICTA (1) (2023)

Keyphrases

speech recognition
cross modal
hidden markov models
speech synthesis
multi modal
language model
speech signal
automatic speech recognition
speech recognizer
visual data
pattern recognition
natural language
image retrieval
contextual information
visual information
speaker identification