It provides new audio and video AI applications related to face recognition and speech recognition for videoconferencing, realizing functions such as non-inductive sign-in, electronic nameplate, real-time subtitles and automatic meeting minutes, etc. It is possible to enjoy conference experiences brought by new technologies through intelligent means, help participants to deal with conference details, enhance conference experiences, improve conference efficiency and serve the whole conference process.
It is possible to complete sign-in and attendance statistics automatically, saving counting time and avoiding potential errors.
It is possible to display participants’ information via virtual nameplate during conferences, which help participants avoid the embarrassment like “Strangers” and makes cross-regional and cross-departmental communication much smoother.
Real-time speech recognition and automatically archiving help participants understand and record conference contents more accurately during and after conferences.
Graphical control interfaces with customized UI design and shortcut keys are easy to use.
Management of users’ faces library ;
1:N face recognition ;
Automatic non-inductive sign-in before conference ;
Automatic electronic nameplate display (names/departments/regions, etc.) during a conference.
Speech to text ;
Real-time subtitle presenting during conference ;
Automatic meeting minutes archiving after conference;
Terminal control via speech.
Touch control panel integration ;
Unified and centralized control of multimedia equipment ;
Conference room peripherals controlling such as curtains, lights and curtains ;
Modes presetting and fast switching .