End-to-End Multi-Channel Transformer for Speech Recognition.
Feng-Ju ChangMartin RadfarAthanasios MouchtarisBrian KingSiegfried KunzmannPublished in: ICASSP (2021)
Keyphrases
- end to end
- multi channel
- speech recognition
- language model
- hidden markov models
- automatic speech recognition
- speech recognizer
- single channel
- pattern recognition
- speaker identification
- speech signal
- wireless ad hoc networks
- multipath
- speech recognition systems
- speech synthesis
- congestion control
- ad hoc networks
- probabilistic model
- maximum likelihood
- mobile devices