Conv-Transformer Transducer: Low Latency, Low Frame Rate, Streamable End-to-End Speech Recognition.
Wenyong HuangWenchao HuYu Ting YeungXiao ChenPublished in: CoRR (2020)
Keyphrases
- speech recognition
- end to end
- low latency
- low frame rate
- frame rate
- high bandwidth
- high speed
- low resolution
- gait recognition
- high throughput
- high resolution
- highly efficient
- hidden markov models
- language model
- real time
- virtual machine
- ad hoc networks
- multipath
- stream processing
- pattern recognition
- mobile nodes
- video sequences
- mobile ad hoc networks
- image processing
- image sequences
- neural network
- data streams