Multi-Head Decoder for End-to-End Speech Recognition.
Tomoki HayashiShinji WatanabeTomoki TodaKazuya TakedaPublished in: INTERSPEECH (2018)
Keyphrases
- end to end
- speech recognition
- rate allocation
- hidden markov models
- automatic speech recognition
- speech processing
- language model
- speech signal
- speech synthesis
- speaker identification
- pattern recognition
- speech recognizer
- speech recognition systems
- speech recognition technology
- congestion control
- noisy environments
- error concealment
- low complexity
- computer vision
- error control
- video coding
- video sequences
- image processing