Parallel Rescoring with Transformer for Streaming On-Device Speech Recognition.
Wei LiJames QinChung-Cheng ChiuRuoming PangYanzhang HePublished in: INTERSPEECH (2020)
Keyphrases
- speech recognition
- hidden markov models
- language model
- speech processing
- speech synthesis
- automatic speech recognition
- speech recognizer
- speech signal
- pattern recognition
- speech understanding
- speaker identification
- noisy environments
- speaker independent
- speech recognition errors
- speech recognition technology
- multimedia
- isolated word
- image processing
- keyword spotting
- handwriting recognition
- n gram
- neural network