In-band voice-assistant/concierge for controlling online meetings

Abstract

An audio conferencing apparatus includes a hardware interface to be coupled to a microphone and speaker assembly, and a network interface to be coupled to a network for audio conferencing with remote audio conferencing devices and for accessing a voice assistant service that operates to assist with the audio conferencing. An audio interceptor is coupled between the hardware interface and the network interface to direct audio over a first voice channel while audio conferencing with the remote audio conferencing devices. The audio interceptor monitors for a trigger command signal during the audio conferencing, and directs audio from the first voice channel to a second voice channel upon detection of the trigger command signal. The second voice channel is used to access a collaboration service via the voice assistant service, with the collaboration service being used to manage audio conferencing in a meeting room in response to a command received by the voice assistant service.

That which is claimed: 
     
         1 . An audio conferencing apparatus comprising:
 a housing;   a hardware interface carried by said housing and coupled to a microphone and speaker assembly;   a network interface carried by said housing, with said network interface to be coupled to a network for audio conferencing with at least one remote audio conferencing device, and for accessing a voice assistant service that operates to assist with the audio conferencing; and   an audio interceptor carried by said housing and coupled between said hardware interface and said network interface, said audio interceptor comprising at least one processor configured to
 direct audio from said hardware interface to said network interface over a first voice channel while audio conferencing with the at least one remote audio conferencing device, 
 monitor for a trigger command signal during the audio conferencing, 
 direct audio from the first voice channel to a second voice channel upon detection of the trigger command signal, with the second voice channel being used to access a collaboration service via the voice assistant service, with the collaboration service being used to manage audio conferencing in a meeting room in response to a command received by the voice assistant service, and 
 mix in the first voice channel a voice assistance audio response from the voice assistant service, directed to a status of the command received by the collaboration service, with audio from the at least one remote audio conferencing device while audio conferencing following the trigger command signal. 
   
     
     
         2 . The audio conferencing apparatus according to  claim 1  wherein the trigger command signal is generated by a user of the audio conferencing apparatus and not a user of the at least one remote audio conferencing device. 
     
     
         3 . The audio conferencing apparatus according to  claim 1  wherein the collaboration service is used to manage audio conferencing in the meeting room in response to querying a calendar associated with the meeting room. 
     
     
         4 . The audio conferencing apparatus according to  claim 1  wherein the mixing performed by said at least one processor includes reducing a volume level of the audio from the at least one remote audio conferencing device to be less than a volume level of the voice assistance audio response. 
     
     
         5 . The audio conferencing apparatus according to  claim 1  wherein said at least one processor in said audio interceptor is further configured to monitor the first voice channel during the audio conferencing for a wake-word, and upon detection of a wake-word, generate the trigger command signal. 
     
     
         6 . The audio conferencing apparatus according to  claim 1  wherein said audio interceptor further comprises a push-to-talk device for providing the trigger command signal in response to a user activating said push-to-talk device. 
     
     
         7 . The audio conferencing apparatus according to  claim 1  wherein the second voice channel is separate from the first voice channel, and wherein said at least one processor in said audio interceptor is further configured to mute the first voice channel so that the audio following the trigger command signal is not received by the at least one remote audio conferencing device. 
     
     
         8 . The audio conferencing apparatus according to  claim 1  wherein said at least one processor in said audio interceptor is further configured to direct the audio following the trigger command signal to the second voice channel. 
     
     
         9 . The audio conferencing apparatus according to  claim 8  wherein said at least one processor in said audio interceptor is further configured to access in the second voice channel the voice assistant service via said network interface. 
     
     
         10 . The audio conferencing apparatus according to  claim 9  wherein said at least one processor in said audio interceptor is further configured to generate the trigger command signal, with the trigger command signal being used to direct the audio following the trigger command signal to the voice-assistance service. 
     
     
         11 . A method for operating an audio conferencing apparatus, wherein the audio conferencing apparatus includes a hardware interface coupled to a microphone and speaker assembly; a network interface to be coupled to a network for audio conferencing with at least one remote audio conferencing device, and for accessing a voice assistant service that operates to assist with the audio conferencing; and an audio interceptor coupled between the hardware interface and the network interface, the method comprising:
 directing audio from the hardware interface to the network interface over a first voice channel while audio conferencing with the at least one remote audio conferencing device;   monitoring for a trigger command signal during the audio conferencing;   directing audio from the first voice channel to a second voice channel upon detection of the trigger command signal, with the second voice channel being used to access a collaboration service via the voice assistant service, with the collaboration service being used to manage audio conferencing in a meeting room in response to a command received by the voice assistant service; and   mixing in the first voice channel a voice assistance audio response from the voice assistant service, directed to a status of the command received by the collaboration service, with audio from the at least one remote audio conferencing device while audio conferencing following the trigger command signal.   
     
     
         12 . The method according to  claim 11  wherein the trigger command signal is generated by a user of the audio conferencing apparatus and not a user of the at least one remote audio conferencing device. 
     
     
         13 . The method according to  claim 11  wherein the collaboration service is used to manage audio conferencing in the meeting room in response to querying a calendar associated with the meeting room. 
     
     
         14 . The method according to  claim 11  further comprising monitoring the first voice channel during the audio conferencing for a wake-word, and upon detection of a wake-word, generating the trigger command signal. 
     
     
         15 . The method according to  claim 11  wherein the audio interceptor further comprises a push-to-talk device for providing the trigger command signal in response to a user activating the push-to-talk device. 
     
     
         16 . The method according to  claim 11  wherein the second voice channel is separate from the first voice channel, and further comprising muting the first voice channel so that the audio following the trigger command signal is not received by the at least one remote audio conferencing device. 
     
     
         17 . The method according to  claim 11  further comprising directing the audio following the trigger command signal to the second voice channel. 
     
     
         18 . The method according to  claim 17  further comprising accessing in the second voice channel the voice assistant service via the network interface. 
     
     
         19 . The method according to  claim 18  further comprising generating the trigger command signal, with the trigger command signal being used to direct the audio following the trigger command signal to the voice-assistance service. 
     
     
         20 . A non-transitory computer readable medium for an audio conferencing apparatus, wherein the audio conferencing apparatus includes a hardware interface coupled to a microphone and speaker assembly; a network interface to be coupled to a network for audio conferencing with at least one remote audio conferencing device, and for accessing a voice assistant service that operates to assist with the audio conferencing; and an audio interceptor coupled between the hardware interface and the network interface, the non-transitory computer readable medium having a plurality of computer executable instructions for causing the audio conferencing apparatus to perform steps comprising:
 directing audio from the hardware interface to the network interface over a first voice channel while audio conferencing with the at least one remote audio conferencing device;   monitoring for a trigger command signal during the audio conferencing;   directing audio from the first voice channel to a second voice channel upon detection of the trigger command signal, with the second voice channel being used to access a collaboration service via the voice assistant service, with the collaboration service being used to manage audio conferencing in a meeting room in response to a command received by the voice assistant service; and   mixing in the first voice channel a voice assistance audio response from the voice assistant service, directed to a status of the command received by the collaboration service, with audio from the at least one remote audio conferencing device while audio conferencing following the trigger command signal.