Multi-modality active speaker detection

A computer-implemented method comprising:

• as implemented by a first computing system comprising one or more processors configured to execute specific instructions,
• receiving communication data associated with each of a plurality of communication devices in a first physical location, wherein first communication data received from a first communication device of the plurality of communication devices comprises first modality data in a first modality and second modality data in a second modality;
• determining, based on the first modality data, that the first communication device is a candidate device for identifying an active speaker;
• determining a second communication device of the plurality of communication devices is a second candidate device for identifying the active speaker based on comparing a first location associated with the first communication device to a second location associated with the second communication device to determine the second communication device is within a threshold distance of the first communication device;
• determining, based on data of at least one of the first modality or the second modality, received from the second communication device, the second communication device is not associated with the active speaker;
• determining, based on the second modality data, that the first communication device is associated with the active speaker;
• and
• transmitting speaker data regarding the active speaker to a second computing system in a second physical location, wherein the speaker data comprises an identifier associated with the active speaker.

A system comprising a computing device comprising:

• a computer-readable memory and one or more processors, wherein the one or more processors are configured to:
• receive communication data associated with each of a plurality of communication devices in a first physical location, wherein first communication data received from a first communication device of the plurality of communication devices comprises first modality data in a first modality and second modality data in a second modality;
• determine, based on the first modality data, that the first communication device is a candidate device for identifying an active speaker;
• determine a second communication device of the plurality of communication devices is a second candidate device for identifying the active speaker based on comparing a first location associated with the first communication device to a second location associated with the second communication device to determine the second communication device is within a threshold distance of the first communication device;
• determine, based on data of at least one of the first modality or the second modality, received from the second communication device, the second communication device is not associated with the active speaker;
• determine, based on the second modality data, that the first communication device is associated with the active speaker;
• and
• transmit speaker data regarding the active speaker to a second computing system in a second physical location, wherein the speaker data comprises an identifier associated with the active speaker.