Speech Discrimination in Real-World Group Communication Using Audio-Motion Multimodal Sensing.
Takayuki NozawaMizuki UchiyamaKeigo HondaTamio NakanoYoshihiro MiyakePublished in: Sensors (2020)
Keyphrases
- group communication
- audio visual
- visual data
- multi stream
- fault tolerance
- multi modal
- audio stream
- broadcast news
- motion estimation
- multimedia
- visual information
- audio features
- computing environments
- speaker identification
- text to speech
- speech recognition
- multimodal interfaces
- key management
- sensor networks
- visual speech
- speech signal
- multi party
- real time