Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition.

Yonatan Belinkov Ahmed Ali James R. Glass

Published in: INTERSPEECH (2019)

Keyphrases

end to end
automatic speech recognition
speech recognition
speech sounds
speech signal
word error rate
broadcast news
speech retrieval

hidden markov models
speech recognizer
conversational speech
noisy environments
spoken term detection
language model
congestion control
pattern recognition

admission control
spoken words
speaker adaptation
acoustic models
recognition errors
word recognition
internet protocol
speech synthesis

scalable video
spontaneous speech
spoken document retrieval
speaker identification
application layer
handwriting recognition
computer vision
real world