E2E-SINCNET: Toward Fully End-To-End Speech Recognition.
Titouan ParcolletMohamed MorchidGeorges LinarèsPublished in: ICASSP (2020)
Keyphrases
- scalable video
- speech recognition
- end to end
- speech signal
- speech processing
- speech synthesis
- language model
- pattern recognition
- hidden markov models
- automatic speech recognition
- speech recognizer
- speech recognizers
- speech recognition technology
- congestion control
- speaker identification
- speaker independent
- noisy environments
- speech recognition systems
- speaker adaptation
- speaker dependent