Abstract: Systems and methods for enhancing group sound during a networked conference are provided. A computer device accesses audio data, detects a first group sound in the audio data, and generates a first group sound identifier that identifies the first group sound. The computer device is one of a plurality of computer devices connected to the networked conference. The computer device transmits the first group sound identifier to a network server and receives a control signal from the network server. The network server receives multiple group sound identifiers from the plurality of computer devices and generates the control signal based on the multiple group sound identifiers. The multiple group sound identifiers include the first group sound identifier and a second group identifier. The control signal includes the second group sound identifier. The computer device reproduces a second group sound based on the second group sound identifier.

Abstract: Example methods and systems provide a workplace assistant application that can detect electronic content associated with a remote user and access multiple communication channels connected to a workplace assistant client application. The system can submit the electronic content to one or more predictive models to provide a context for the electronic content. The context is based at least in part on information from multiple channels. The system can generate, using the predictive model(s), an action item based at least in part on the context of the electronic content as well as display or store the action item using the workplace assistant client application. An action item, as examples, can be a “to do” item, a meeting agenda, a reminder, a meeting, a task, or some combination of one or more of these.

Abstract: One example method includes receiving, during a virtual conference from a client device, a request to generate a real-time summary of the virtual conference, a plurality of client devices participating in the virtual conference and exchanging audio and video streams; receiving, during the virtual conference, a plurality of utterances generated by automatic speech recognition (“ASR”) of the audio streams; generating a group of consecutive utterances from the plurality of utterances; determining a segment based on the group of consecutive utterances; generating, using a large language model (“LLM”), a segment summary based on the segment; and providing the segment summary to the client device.

Abstract: Some examples relate to locally storing a chat conversation history at an on-premises data center. As one example, a system can receive a chat message from a first client device of a first participant in a chat conversation. In response to receiving the chat message, the system can determine a data center associated with the first participant. The system can then transmit the text chat message to a server node in the data center. The server node can be configured to transmit a command to a database system of the data center. The command can be configured to cause the database system to store a copy of the text chat message in a chat log associated with the chat conversation. The system can also transmit the text chat message to a second client device of a second participant in the chat conversation.

Abstract: One example method includes joining, by a client application executed by a client device, a virtual conference hosted by a virtual conference provider, a plurality of participants attending the virtual conference; receiving, by the client application, a question associated with the virtual conference; generating a query context based on a real-time transcript of the virtual conference; providing the query context and the question to a trained large language model (“LLM”); and receiving a response from the LLM based on the question and the query context.

Abstract: One example method includes transmitting, by a client device, a request for a reduced large language model (“LLM”) to a remote server; receiving, by the client device from the remote server, and storing the reduced LLM, the reduced LLM based on a trained general LLM; receiving, by the client device, a request to generate content using the reduced LLM; providing the request to the reduced LLM; and receiving generated content from the reduced LLM based on the request.

Abstract: Systems and methods for providing instant processing of virtual meeting recordings are provided.

Abstract: One disclosed example method includes a video conference provider establishing a main meeting of a video conference and multiple associated sub-meetings at the request of a host client device associated with a host of the meeting. The method further includes the video conference provider determining that a self-selection mode for the sub-meetings is enabled and transmitting notifications to participant client devices associated with the participants of the meeting. Each notification identifies a list of sub-meetings from which a participant can select a sub-meeting to join. The method further includes the video conference provider receiving and forwarding a request from a participant client device to connect to a selected sub-meeting, and receiving an automatic approval from the host client device. The video conference provider further connects the participant client device to the selected sub-meeting.

Abstract: One example method for mediating participant interactions during a video webinar meeting includes establishing a video webinar meeting; admitting a host and a plurality of participants to the video webinar meeting; not distributing audio streams from the plurality of participants to other participants in the video webinar meeting; receiving, from a first participant, a first submission to be posed during the video webinar meeting; determining a priority for the first submission based on one or more parameters; and distributing an audio stream associated with the first participant to the host and the remaining plurality of participants based on the priority to enable the first participant to pose the first submission.

Abstract: Systems and methods for capturing actions of local participants and conveying those actions to remote participants in a virtual conference are provided. A virtual conference device connects to one or more client devices associated with one or more remote participants in a virtual conference. The virtual conference device is also connected with one or more user devices associated with one or more local participants within a common area. The virtual conference device receives sensor data related to a local participant associated with a user device within the common area during the video conference. The virtual conference device determines a physical action of the local participant associated with the user device at least based on the sensor data. The virtual conference device provides a representation of the physical action to the one or more client devices associated with the one or more remote participants.

Abstract: Provided herein are systems and methods for delta models for providing privatized speech-to-text during virtual meetings. In one embodiment, a system may include a non-transitory computer-readable medium; a communications interface; and a processor. The processor may be configured to execute processor-executable instructions to: join a virtual meeting. Each participant in the virtual meeting may exchange audio streams with other participants in the virtual meeting. The instructions may include receiving, from a video conference provider, a local model for speech recognition. The local model may be a copy of a centralized model. The instructions may include performing speech recognition using the local model on the audio streams.

Abstract: One example method includes receiving, from a first client device, a request to join a video conference, the video conference having a main meeting, creating, in response to the request, a sub-meeting associated with the main meeting, connecting the first client device to the sub-meeting, connecting a host client device to the sub-meeting simultaneously with the host client device being connected to the main meeting, the host client device associated with a host of the main meeting, receiving first multimedia content from the first client device, and providing the first multimedia content to the host client device.

Abstract: Systems and methods for aggregation and distribution of diverse multimedia feeds are provided herein. In an aspect, a method including establishing, by a video conference provider, a virtual meeting having a plurality of participants is provided. Each participant joined to the virtual meeting may use a respective client device to exchange one or more audio or video streams via the virtual meeting. The method may also include receiving, from a first client device, a request to share a multimedia stream from an external source with one or more of the client devices during the virtual meeting. Responsive to the request, the method may include receiving a connection to the multimedia stream from the external source and transmitting, by the video conference provider, the multimedia stream from the external source to the one or more client devices via the virtual meeting.

Abstract: One method for multimodal meeting segmentation includes receiving a meeting recording and a transcript, the meeting recording comprising a first media stream; generating, using a trained machine learning (“ML”) model, a first set of embeddings corresponding to the first media stream and a second set of embeddings corresponding to the transcript; generating a first set of segments based on the first set of embeddings and a second set of segments based on the second set of embeddings; generating a final set of segments based on the first and second sets of segments; and associating the final set of segments with the meeting recording and storing the final set of segments.

Abstract: Systems and methods of message filtering in a multi-region multi-active architecture are provided. A client device receives a data message, the data message comprising a region tag and an account tag. The client device determines whether the region tag corresponds to a region server assigned to serve the client device. In response to determining the region tag corresponds to the region server assigned to serve the client device, the client device determines whether an account identification (ID) associated with the client device matches the account tag of the data message. In response to determining the account ID matches the account tag, the client device consumes the data message.

Abstract: Example methods and systems for automatic task generation is provided. A communication platform receives an instruction to generate one or more task items associated with a virtual communication session related to a user. The communication platform accesses virtual communication data associated with the virtual communication session. The communication platform generates a task item based on the virtual communication data using a generative artificial intelligence (AI) model. The communication platform provides the task item to the user.

Abstract: System and methods for running conference applications before, during, and after a network conference. In an embodiment, a method is provided for running a conference application before joining a network conference. The method includes activating a client application, selecting a conference application from a plurality of conference applications, running the conference application from the client application before joining a network conference, and joining the network conference using the client application.

Abstract: Example methods and systems provide automatic audio equalization for online conferences. A target, ideal, audio frequency response for use in online conferencing audio can be designed and preset for reference, and the equalizer can operate in real time to reach the target frequency response for any input. The equalizer can selectively apply per-band equalization to the audio signal as needed to adjust an energy value for each of multiple frequency bands to produce an output audio signal that that can be, as an example, routed through meeting servers or other infrastructure to other conference participants. The equalization can compensate for conditions local to a speaker that would otherwise adversely affect audio quality.

Abstract: One example method includes executing a video conference application at a client device; determining, at the client device, based on one or more of a plurality of real time performance measures or a user input, the presence of a fault associated with a currently-active video conference executed in the video conference application, and determining, at the client device by the video conference application, a plurality of potential causes of the fault based at least in part on the plurality of real time performance measures. The example method further includes providing, at the client device by the video conference application, a notification of the presence of the fault to the user, and generating, at the client device by the video conference application, a list of potential actions to alleviate the fault in real time, the list of potential actions based at least in part on the plurality of potential causes of the fault.