Contextual Phonetic Pretraining for End-to-end Utterance-level Language and Speaker Recognition.

Shaoshi Ling Julian Salazar Katrin Kirchhoff

Published in: CoRR (2019)

Keyphrases

end to end
speaker recognition
speech recognition
speaker identification
gaussian mixture model
vector quantization
congestion control
contextual information
speech signal
speaker verification
pattern recognition
hidden markov models
spoken language
natural language
probabilistic neural network