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: Interspeech (2021)
Keyphrases
- end to end
- speech recognition
- scalable video
- rate adaptation
- hidden markov models
- language model
- speech processing
- automatic speech recognition
- speech synthesis
- speech signal
- pattern recognition
- speech recognizer
- question answering
- noisy environments
- speech recognition systems
- natural language processing
- data streams
- speech recognition technology
- video streaming
- congestion control
- speaker identification
- transport protocol
- information extraction
- neural network
- speaker adaptation
- isolated word
- content delivery
- coding scheme
- image processing