An Investigation of Positional Encoding in Transformer-based End-to-end Speech Recognition.
Fengpeng YueTom KoPublished in: ISCSLP (2021)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- automatic speech recognition
- speech signal
- speech synthesis
- speech processing
- speech recognition systems
- congestion control
- pattern recognition
- speech recognition technology
- speaker independent
- speech recognizer
- speech recognizers
- noisy environments
- speaker identification
- scalable video
- isolated word
- speaker dependent
- mode selection