Multi-Turn RNN-T for Streaming Recognition of Multi-Party Speech.
Ilya SklyarAnna PiunovaXianrui ZhengYulan LiuPublished in: ICASSP (2022)
Keyphrases
- multi party
- recognition engine
- human communication
- privacy preserving
- recurrent neural networks
- speech recognition
- recognition rate
- speech corpus
- automatic speech recognition systems
- nearest neighbor
- speech signal
- audio video
- object recognition
- pattern recognition
- data streams
- mental states
- software engineering
- virtual humans
- noisy environments
- speech recognition systems
- feature extraction
- speech sounds
- virtual environment
- audio visual
- neural network
- speech synthesis
- fair exchange
- data mining