Streaming End-to-End Target-Speaker Automatic Speech Recognition and Activity Detection.
Takafumi MoriyaHiroshi SatoTsubasa OchiaiMarc DelcroixTakahiro ShinozakiPublished in: IEEE Access (2023)
Keyphrases
- end to end
- automatic speech recognition
- activity detection
- speech recognition
- scalable video
- speech signal
- rate adaptation
- hidden markov models
- broadcast news
- sequence matching
- congestion control
- speech retrieval
- speaker adaptation
- data streams
- acoustic features
- noisy environments
- spontaneous speech
- conversational speech
- speech synthesis
- document retrieval
- language model
- speaker diarization
- pattern recognition