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: INTERSPEECH (2022)
Keyphrases
- speech recognition
- neural network
- pattern recognition
- hidden markov models
- isolated word
- language model
- speech processing
- wall street journal corpus
- speech synthesis
- training process
- speech signal
- noisy environments
- automatic speech recognition
- speech recognizer
- acoustic models
- speech retrieval
- speech recognition technology
- maximum likelihood
- speech understanding
- speaker recognition
- cepstral coefficients
- speaker independent
- keyword spotting
- vector quantization
- face recognition
- machine learning