Local Monotonic Attention Mechanism for End-to-End Speech Recognition.
Andros TjandraSakriani SaktiSatoshi NakamuraPublished in: CoRR (2017)
Keyphrases
- end to end
- speech recognition
- attention mechanism
- visual attention
- hidden markov models
- saliency map
- language model
- automatic speech recognition
- speech synthesis
- speech recognition technology
- visual attention model
- congestion control
- speech signal
- pattern recognition
- speaker identification
- speech recognizer
- speech recognition systems
- noisy environments
- speaker independent
- eye tracking
- human visual system
- eye movements
- image classification
- video sequences
- image processing
- information retrieval