Login / Signup

Embedding Articulatory Constraints for Low-resource Speech Recognition Based on Large Pre-trained Model.

Jaeyoung LeeMasato MimuraTatsuya Kawahara
Published in: INTERSPEECH (2023)
Keyphrases
  • speech recognition
  • probabilistic model
  • training data
  • pattern recognition
  • pre trained
  • data sets
  • feature space
  • prior knowledge
  • hidden markov models
  • language model
  • speech recognizer