Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognition.
Tianyi XuZhanheng YangKaixun HuangPengcheng GuoAo ZhangBiao LiChangru ChenChao LiLei XiePublished in: CoRR (2023)
Keyphrases
- speech recognition
- hidden markov models
- language model
- speech synthesis
- pattern recognition
- speech understanding
- speech signal
- speech processing
- speaker identification
- speech recognizer
- automatic speech recognition
- speech recognition technology
- contextual information
- noisy environments
- handwriting recognition
- speech recognizers
- neural network
- speech recognition systems
- speaker dependent
- speaker recognition
- mixture model
- speaker independent
- speech recognition errors