Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition.
Kai ZhenHieu Duy NguyenRaviteja ChintaNathan SusanjAthanasios MouchtarisTariq AfzalAriya RastrowPublished in: CoRR (2022)
Keyphrases
- speech recognition
- neural network
- pattern recognition
- language model
- speech processing
- isolated word
- hidden markov models
- wall street journal corpus
- speech understanding
- speaker identification
- speech synthesis
- speech recognizer
- speech signal
- training process
- training set
- noisy environments
- automatic speech recognition
- speech recognition systems
- speaker dependent
- speech recognition technology
- hybrid method
- keyword spotting
- speech retrieval
- feature extraction