Fully Quantizing a Simplified Transformer for End-to-end Speech Recognition.
Alex BieBharat VenkiteshJoao MonteiroMd. Akmal HaidarMehdi RezagholizadehPublished in: CoRR (2019)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- speech processing
- language model
- speech synthesis
- pattern recognition
- congestion control
- speech signal
- automatic speech recognition
- speech recognition technology
- speech recognizer
- speaker identification
- speech retrieval
- noisy environments
- speech recognition systems
- scalable video
- speech recognizers
- speaker dependent
- speaker independent
- computer vision
- machine learning