Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection.
Minglun HanLinhao DongZhenlin LiangMeng CaiShiyu ZhouZejun MaBo XuPublished in: ICASSP (2022)
Keyphrases
- end to end
- fine grained
- speech recognition
- contextual knowledge
- contextual information
- coarse grained
- hidden markov models
- case based reasoning
- speech synthesis
- language model
- speech signal
- speech recognition technology
- access control
- automatic speech recognition
- pattern recognition
- knowledge sources
- congestion control
- context aware
- speaker independent
- information overload
- speaker identification
- speech recognition systems
- speech recognizer
- information retrieval
- n gram
- data lineage
- video sequences