Multi-turn RNN-T for streaming recognition of multi-party speech.
Ilya SklyarAnna PiunovaXianrui ZhengYulan LiuPublished in: CoRR (2021)
Keyphrases
- multi party
- recognition engine
- human communication
- privacy preserving
- recurrent neural networks
- recognition rate
- nearest neighbor
- automatic speech recognition systems
- object recognition
- feature extraction
- speech corpus
- virtual humans
- audio video
- speech recognition
- speech signal
- data streams
- pattern recognition
- domain independent
- mental states
- description language
- automatic speech recognition
- text to speech
- expert systems
- automatic transcription
- neural network