Method for controlling a real-time conversation and real-time communication and collaboration platform
A method for controlling a real-time communication between at least two participants can include identifying, from the at least two participants a first participant as an active speaker in the conversation by using audio signals received from the first participant via a microphone, and activating the digital assistant unit for the first participant. A voice recognition procedure for identifying and transcribing identified voice commands can be used so the transcribed voice commands are analyzed and executed.
1. A method for controlling a real-time communication between at least two participants on a real-time conversation and collaboration platform via a digital assistant unit, wherein the at least two participants are connected to a conferencing application via a communications network establishing the communication, the method comprising:
identifying a first participant from the at least two participants as an active speaker in a conversation by using audio signals received from the first participant via a microphone;
verifying whether the first participant is authorized to access the digital assistant unit;
activating the digital assistant unit for the first participant based on a detection of a predetermined event;
transcribing, in response to a determination that the first participant is authorized to access the digital assistant unit, the audio signals using a voice recognition procedure to generate a transcription; and
analyzing the transcription to identify one or more voice commands included in the audio signals.
2. The method according to claim 1 , wherein the predetermined event is receiving an input for activating the digital assistant unit or a bot of the digital assistant unit.
3. The method according to claim 1 , wherein the predetermined event is the receipt of log-in data from the first participant.
4. The method according to claim 1 , wherein the predetermined event is the verification of the first participant's authorization.
5. The method according to claim 1 , wherein the predetermined event is the detection of a keyword from the audio signals received from the first participant.
6. The method according to claim 1 , wherein the predetermined event is the identification of the matching of an audio sample from the audio signals received from the first participant with at least one pre-recorded voice sample.
7. The method according to claim 1 , wherein, the method further comprises:
establishing an additional audio channel from the first participant to the digital assistant unit in response to the first participant being verified to be authorized to use the digital assistant unit.
8. The method according to claim 7 , wherein the additional audio channel is established via a media server routing the audio signals received from the first participant to the ASR engine via the additional audio channel.
9. The method according to claim 1 , further comprising:
executing the identified one or more voice commands.
10. A real-time communication and collaboration platform comprising:
a first application for processing at least one of an audio signal or a video signal received from at least two participants for enabling a real-time conversation between the at least two participants over a communications network, and
a second application for providing a digital assistant bot of a digital assistant unit for at least one of the at least two participants; the platform configured such that a first participant from the at least two participants is identifiable as an active speaker in a conversation by using audio signals received from the first participant via a microphone and the digital assistant unit is activatable for the first participant based on a detection of a predetermined event, wherein, in response to a determination that the first participant is authorized to access the digital assistant unit, the audio signals received from the first participant are transcribed using a voice recognition procedure to generate a transcription, and the transcription is analyzed to identify one or more voice commands therefrom.
11. The real-time communication and collaboration platform according to claim 10 , wherein the digital assistant unit comprises
an Automatic Speech Recognition (ASR) engine,
a text-to-speech engine,
a Natural Language Understanding (NLU) unit,
a media server, and
a virtual Artificial Intelligence (AI) endpoint.
12. The real-time communication and collaboration platform according to claim 11 , wherein the ASR engine performs the voice recognition procedure for transcribing the audio signals.
13. The real-time communication and collaboration platform according to claim 11 , wherein the virtual AI endpoint is a digital assistant bot.
14. The real-time communication and collaboration platform according to claim 13 comprising:
an interface to the digital assistant bot.
15. The real-time communication and collaboration platform according to claim 10 , wherein the digital assistant unit further comprises:
an Active Speaker Notification (ASN) module, and
an authentication and authorization module.
16. The real-time communication and collaboration platform according to claim 10 , wherein the identified one or more voice commands are executed.