Joint CTC/attention decoding for end-to-end speech recognition.
Takaaki HoriShinji WatanabeJohn R. HersheyPublished in: ACL (1) (2017)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- speech processing
- language model
- automatic speech recognition
- pattern recognition
- speech signal
- speech synthesis
- speech recognition technology
- congestion control
- speech recognition systems
- speech recognizer
- noisy environments
- speaker identification
- speaker independent
- scalable video
- rate allocation
- image processing