Streaming Target-Speaker ASR with Neural Transducer.
Takafumi MoriyaHiroshi SatoTsubasa OchiaiMarc DelcroixTakahiro ShinozakiPublished in: CoRR (2022)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- data streams
- network architecture
- noisy environments
- speaker verification
- neural network
- speaker identification
- target detection
- target tracking
- video streaming
- target object
- vocal tract
- neural fuzzy
- data streaming
- speech retrieval
- speaker recognition
- real time
- spoken words
- multiple targets
- stream processing
- associative memory
- language model
- feature extraction
- multimedia
- data sets