Streaming Target-Speaker ASR with Neural Transducer.
Takafumi MoriyaHiroshi SatoTsubasa OchiaiMarc DelcroixTakahiro ShinozakiPublished in: INTERSPEECH (2022)
Keyphrases
- automatic speech recognition
- speech recognition
- network architecture
- data streams
- biologically plausible
- neural network
- target tracking
- real time
- speech signal
- hidden markov models
- pattern recognition
- image sequences
- information retrieval
- biologically inspired
- video streaming
- bio inspired
- stream processing
- scalable video
- neural computation
- speech retrieval
- nonlinear predictive control