UniEnc-CASSNAT: An Encoder-Only Non-Autoregressive ASR for Speech SSL Models.
Ruchao FanNatarajan Balaji ShankaAbeer AlwanPublished in: IEEE Signal Process. Lett. (2024)
Keyphrases
- autoregressive
- moving average
- random fields
- speech recognition
- non stationary
- random field models
- automatic speech recognition
- gaussian markov random field
- autoregressive model
- computer vision
- spectrum analysis
- semi supervised learning
- probabilistic model
- machine learning
- maximum entropy
- speech signal
- semi supervised
- artificial neural networks
- feature selection