Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion.
Duc LeMahaveer JainGil KerenSuyoun KimYangyang ShiJay MahadeokarJulian ChanYuan ShangguanChristian FuegenOzlem KalinliYatharth SarafMichael L. SeltzerPublished in: CoRR (2021)
Keyphrases
- end to end
- speech recognition
- scalable video
- rate adaptation
- hidden markov models
- language model
- speech signal
- pattern recognition
- question answering
- speech synthesis
- congestion control
- speech recognizer
- speech processing
- speech recognition systems
- automatic speech recognition
- noisy environments
- speaker identification
- video streaming
- data streams
- speech recognition technology
- speaker independent
- speaker dependent
- natural language processing
- information extraction
- image processing