Hybrid CTC/Attention Architecture for End-to-End Speech Recognition.
Shinji WatanabeTakaaki HoriSuyoun KimJohn R. HersheyTomoki HayashiPublished in: IEEE J. Sel. Top. Signal Process. (2017)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- pattern recognition
- speech processing
- automatic speech recognition
- speech recognition systems
- speech recognizer
- speech recognition technology
- admission control
- speech synthesis
- speech signal
- congestion control
- speaker identification
- noisy environments
- speaker independent
- network architecture
- differentiated services
- speaker dependent
- speech recognizers
- computer vision
- isolated word
- audio visual speech recognition