Shared speakerphone system for multiple devices in a conference room
A speakerphone system is shared with multiple participant devices of participants in a physical meeting that are using a web conferencing service. An active speaker is identified from the participants. The participant device of the active speaker is switched, such that the speakerphone system receives and renders audio of the active speaker. Video of the participant device of the active speaker is enabled, such that the web conferencing service displays the video to the participant devices.
1 . A computer-implementable method for sharing a speakerphone system with multiple participant devices comprising:
identifying an active speaker of a group of participants in a physical meeting setting using a web conferencing service;
choosing a participant device of the identified active speaker;
sending audio of the identified active speaker to the web conferencing service, wherein the web conferencing service provides audio to the speakerphone system; and
enabling video captured by the participant device to be shown by the web conferencing service on all participant devices of the group of participants,
wherein the identifying comprises enrolling voice signatures each associated with a participant's voice of the group of participants and identifying the active speaker using an enrolled voice signature, wherein the enrolled voice signatures are stored in a common dictionary configured to be accessed by each participant device.
2 . The computer-implementable method of claim 1 , wherein the enrolled voice signatures are associated with participant devices.
3 . The computer-implementable method of claim 1 , wherein the identifying is performed by capturing a voice of the active speaker, generating a voice signature based on the captured voice, and comparing the generated signature to the enrolled voice signature.
4 . The computer-implementable method of claim 1 , wherein the identifying is performed by active speaker recognition recognizing movement of lips of the active speaker.
5 . The computer-implementable method of claim 1 , wherein the choosing is performed by the participant device.
6 . The computer-implementable method of claim 1 , wherein the choosing is performed by the speakerphone system.
7 . The computer-implementable method of claim 1 , wherein the enrolled voice signatures are associated with unique identifiers.
8 . The computer-implementable method of claim 1 , further comprising receiving voice input of participants and implementing recognition and enrollment of participant voices.
9 . The computer-implementable method of claim 8 , further comprising recognizing the enrolled voice signature is associated with the active speaker when the active speaker speaks into the speakerphone system.
10 . The computer-implementable method of claim 1 , wherein the voice input is processed to create the voice signatures associated with the participants by an active machine learning model.
11 . The computer-implementable method of claim 1 , wherein the identifying further comprises creating device information pairs associating participants with participant devices, wherein the device information pairs are stored in the common dictionary.
12 . A system comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations for sharing a speakerphone system with multiple participant devices and comprising instructions executable by the processor to:
identify an active speaker of a group of participants in a physical meeting setting using a web conferencing service;
choose a participant device of the identified active speaker;
send audio of the identified active speaker to the web conferencing service, wherein the web conferencing service provides audio to the speakerphone system; and
enable video captured by the participant device to be shown by the web conferencing service on all participant devices of the group of participants,
wherein the identifying comprises enrolling voice signatures each associated with a participant's voice of the group of participants and identifying the active speaker through an enrolled voice signature, wherein the enrolled voice signatures are stored in common dictionary configured to be accessed by each participant device.
13 . The system of claim 12 , wherein the identifying is performed by active speaker recognition recognizing movement of lips of the active speaker.
14 . The system of claim 12 , wherein the choosing is performed by the speakerphone system.
15 . A non-transitory, computer-readable storage medium embodying computer program code for sharing a speakerphone system with multiple participant devices, the computer program code comprising computer executable instructions to:
identify an active speaker of a group of participants in a physical meeting setting using a web conferencing service;
choose a participant device of the identified active speaker;
send audio of the identified active speaker to the web conferencing service, wherein the web conferencing service provides audio to the speakerphone system; and
enable video captured by the participant device to be shown by the web conferencing service on all participant devices of the group of participants,
wherein the identifying comprises enrolling voice signatures each associated with a participant's voice of the group of participants and identifying the active speaker through an enrolled voice signature, wherein the enrolled voice signatures are stored in common dictionary configured to be accessed by each participant device.
16 . The non-transitory, computer-readable storage medium of claim 15 , wherein the enrolled voice signatures are associated with participant devices.
17 . The non-transitory, computer-readable storage medium of claim 15 , wherein the identifying is performed by active speaker recognition recognizing movement of lips of the active speaker.
18 . The non-transitory, computer-readable storage medium of claim 15 , wherein choosing the participant device is performed by one participant device of the multiple participant devices.
19 . The non-transitory, computer-readable storage medium of claim 15 , wherein choosing the participant device is performed by the speakerphone system.
20 . The non-transitory, computer-readable storage medium of claim 15 , wherein the participant devices are configured to be chosen and switched by a selector switch hub.