4-bit Conformer with Native Quantization Aware Training for Speech Recognition.
Shaojin DingPhoenix MeadowlarkYanzhang HeLukasz LewShivani AgrawalOleg RybakovPublished in: CoRR (2022)
Keyphrases
- speech recognition
- wall street journal corpus
- hidden markov models
- isolated word
- automatic speech recognition
- language model
- speech synthesis
- speech signal
- pattern recognition
- acoustic models
- speech processing
- speech recognition technology
- training process
- speech understanding
- speech recognition systems
- noisy environments
- speech recognizer
- speaker dependent
- speaker identification
- discriminative training
- keyword spotting
- speaker independent
- feature extraction
- video retrieval
- neural network
- speech recognizers
- mixture model
- background noise