UniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL Models.

Ruchao Fan Natarajan Balaji Shanka Abeer Alwan

Published in: CoRR (2024)

Keyphrases

autoregressive
non stationary
moving average
random fields
gaussian markov random field
automatic speech recognition
random field models
speech recognition
autoregressive model
speech signal
autoregressive moving average
computational complexity
motion estimation
least squares
maximum likelihood