Abstract: A conference system automatically detects a topic in a discussion between two or more participants in a conference based on a transcription of an audio component of the conference. The conference system determines that the discussion is a side conversation based on a determination that the topic is not related to any discussion points of the conference. The conference system determines which participants are related to the side conversation and schedules a future conference between these participants. The conference system generates one or more discussion points for the future conference based on the topic.

Abstract: A portion of speech represented in an audio stream of a conference participant is removed based on a determination that the portion of the speech corresponds to language identified as undesirable. An audio stream representing speech of a user of a participant device connected to a conference is obtained. The audio stream is processed to detect that a portion of the speech corresponds to language identified as undesirable within an audio profile. A modified audio stream is produced by removing the portion of the speech from the audio stream. An output, within the conference, of the modified audio stream is then caused in place of the audio stream.

Abstract: A portion of an audio stream representing speech of a conference participant is filtered based on a determination that the portion of the audio stream corresponds to a predefined sensitive topic. An audio stream representing speech of a user of a participant device connected to a conference is obtained. First hash values are determined for portions of the speech. A determination is made, by comparing the first hash values against second hash values for records of a data store, that a portion of the speech corresponds to a predefined sensitive topic indicated within the records. A filter is applied against the portion of the speech to produce a modified audio stream within which the predefined sensitive topic is sanitized. An output, within the conference, of the modified audio stream is then caused in place of the audio stream.

Abstract: The audio stream of a participant to a conference is modified within the conference to change a perceptible output of a characteristic of speech represented by the audio stream. An audio stream is obtained from a participant device connected to a conference. The audio stream represents speech of a user of the participant device. A user request to modify a first characteristic of the speech is initiated within the conference. The first characteristic is modified without modifying other characteristics of the speech to produce a modified audio stream, such that a second characteristic of the speech remains unmodified within the modified audio stream. An output of the modified audio stream within the conference is then caused in place of the audio stream. The audio stream modification as disclosed herein may be performed while the conference remains ongoing or during playback of a recording of the conference.

Abstract: A system may receive, from a computing device that is not connected to a conference to which one or more participant devices are connected, a message including text entered by a user of the computing device. The system may determine a permission for enabling communications between the computing device and the one or more participant devices by authenticating a credential associated with the computing device. The system may transmit, based on the permission, the message to the one or more participant devices during the conference. In some implementations, the system may invoke speech synthesis software during the conference to produce machine-generated speech representative of the message. The speech synthesis software may use a spoken voice model of the user, generated using recorded voice samples of the user, to produce the machine-generated speech.

Abstract: Conference item selection is automated by a server that retrieves one or more items from a data store based on a determination that the text includes one or more keywords or a change in the subject of the call. The keywords can include phrases. The retrieved items include one or more of scripts, articles, manuals, daily bulletins regarding a system state, or any resource that can be used to assist with a customer call or interaction. The software running on the server generates a user interface (UI) output based on the retrieve items, and transmits the UI output to an agent device. Software running on the agent device receives the UI output and displays the retrieved items on a display of the agent device.

Abstract: A conference system automatically detects a topic in a discussion between two or more participants in a conference based on a real-time transcription of an audio component of the conference. The conference system determines that the discussion is a side conversation based on a determination that the topic is not related to any discussion points of the conference. The conference system determines which participants are related to the side conversation and schedules a future conference between these participants. The conference system generates one or more discussion points for the future conference based on the topic.

Abstract: A callback action is enabled for a first user in association with a voice message (VM) that is in a shared VM inbox. A determination is made that the VM is not responded to within a response time. Responsive to determining that the VM is not responded to within the response time, the VM is reassigned from the first user to a second user. Responsive to reassigning the VM from the first user to the second user, the callback action is enabled for the second user and is disabled for the first user.

Abstract: A conference system transmits a first graphical output for display on a panel interface associated with a conference. Prior to the client device joining the conference, the conference system determines participant information based on a request. The conference system transmits a second graphical output to the client device to display the participant information without the client device having to join the conference.

Abstract: A conferencing system transmits a graphical output associated with a conference that is in progress to a client device for display without requiring the client device to connect to the conference. Prior to the client device connecting to the conference, the conferencing system grants the client device access to an in-conference communication application based on a request to communicate with a participant device. The conferencing system receives a chat message from the client device via the in-conference communication application. The conferencing system updates a topic of the conference based on the chat message.

Abstract: Agent conversation item selection is automated by a server that automatically detects speech in a call and converts that speech to text. Software running on the server retrieves one or more items from a data store based on a determination that the text includes one or more keywords or a change in the subject of the call. The keywords can include phrases. The retrieved items include one or more of scripts, articles, manuals, daily bulletins regarding a system state, or any resource that can be used to assist with a customer call or interaction. The software running on the server generates a user interface (UI) output based on the retrieve items, and transmits the UI output to an agent device. Software running on the agent device receives the UI output and displays the retrieved items on a display of the agent device.

Abstract: A conference system obtains information associated with a conference that is in progress. The conference system transmits a graphical output associated with the conference to a client device for display. Prior to the client device joining the conference, the conference system receives a message to initiate a communication with a participant device that is present in the conference. The conference system grants the client device access to an in-conference communication application associated with the conference in progress to communicate with the participant device without the client device having to join the conference.

Abstract: A voice message (VM) received from a phone number is associated with a shared VM inbox that is accessible to a group of users. The group of users includes a first user and a second user. The VM is assigned to the first user. The first user is determined not to have responded to the VM within a predefined response time. Responsive to the determination that the first user did not respond to the VM within the predefined response time, the VM is reassigned to the second user; a callback action associated with the VM is enabled for the second user; and the callback action is disabled for the first user. A status associated with the VM is updated based on performance of the callback action.

Abstract: A conferencing system transmits a first graphical output associated with a conference to a client device for display without requiring the client device to connect to the conference. Prior to the client device connecting to the conference, the conferencing system receives a request for participant information of the conference. The conferencing system determines the participant information based on the request. The conferencing system transmits a second graphical output to the client device to display the participant information on a display of the client device.

Abstract: A conference participant is provided replay content during a conference responsive to the conference participant needing content and/or context of current conversations. During the conference, a replay request is received, which may be initiated by the conference participant or other participants or automatically based on an event such as detecting a topic relevant to the conference participant, detecting a request associated with a name of the conference participant, or detecting inattentiveness of the conference participant. Content is obtained from a buffer for a period of time relative to or associated with the replay request. The content is annotated based on one or more annotation inputs. Device and user settings associated with the conference participant are used to determine a presentation mode for the replay content. Based on that determination, the replay content is presented to the conference participant to guide discussions.

Abstract: A conference participant is provided replay content during a conference responsive to the conference participant needing content and/or context of current conversations. During the conference, a replay request is received, which may be initiated by the conference participant or other participants or automated my software, such as based on an event detected using a real-time transcription of the conference. For example, the event may relate to a topic relevant to the conference participant or a request associated with a name of the conference participant. Content is obtained from a buffer for a period of time relative to or associated with the replay request. The content is annotated based on one or more annotation inputs. Device and user settings associated with the conference participant are used to determine a presentation mode for the replay content. Based on that determination, the replay content is presented to the conference participant to guide discussions.

Abstract: The server receives a response accepting a task from a device. The server assigns the task to a user of the device. The server transmits an indication that the task was assigned to the user of the device.

Abstract: Video-assisted presence detection is used to enhance a user experience in telephony communications. Image data, video data, or both, from a camera are used to determine whether a user is present at their device before a call is transferred to him or her. The video-assisted presence detection can be implemented based on a privacy setting. For example, one implementation allows a system to have partial access to a detector to detect user presence without capturing facial information, and without identifying that person. Another implementation allows the system to have partial access to the detector to detect user presence without having access to a video feed of the detector.

Abstract: A meeting host or moderator can control communications among participants in virtual breakout rooms without requiring the host to join a breakout room as a participant. The host can run conferencing software to instantiate a meeting room and breakout rooms associated with the meeting room. The host can control communications in the breakout rooms, such as by transmitting and/or receiving content through one or more channels established by the conferencing software. The host can transmit and/or receive content such as a real time audio stream, a transcription of the audio stream, a screen or window being shared, chat messages, and the like, without joining the breakout room.

Abstract: A server transmits a task to client devices using push-to-talk (PTT). The server receives a response accepting the task from a device of the client devices. The server assigns the task to a user of the device. The server transmits an indication that the task was assigned to the user of the device to at least a subset of the client devices.