Low-Latency Lightweight Streaming Speech Recognition with 8-Bit Quantized Simple Gated Convolutional Neural Networks.
Jinhwan ParkXue QianYoungmin JoWonyong SungPublished in: ICASSP (2020)
Keyphrases
- lightweight
- speech recognition
- low latency
- convolutional neural networks
- hidden markov models
- stream processing
- continuous query processing
- speech synthesis
- speech signal
- language model
- automatic speech recognition
- speech recognition technology
- high throughput
- noisy environments
- speaker identification
- pattern recognition
- speech recognizer
- real time
- wireless sensor networks
- block cipher
- highly efficient
- speaker independent
- neural network
- database systems
- data streams
- low complexity