Abstract: A real-time transcript of a portion of an ongoing conference is generated. Based on the real-time transcript, it is determined that a topic-of-interest of a user who is not currently participating in the conference is referenced. A voting interface is presented to at least some participants of the ongoing conference, and respective votes are received from those participants. A notification indicative of the topic-of-interest and the ongoing conference is then transmitted to the user based on the respective votes.

Abstract: An input to schedule a future conference is received. The input identifies a list of topics and a total time scheduled for the future conference. Time allotments for the list of topics are determined based on historical conference data. The time allotments are scaled based on a total time weight indicative of the total time to generate scaled time allotments within that total time.

Abstract: A push-to-talk server receives a request from a client device to initiate a push-to-talk communication with one or more recipient devices. The push-to-talk server receives, from the client device, an audio recording recorded during a latency period between initiation of the push-to-talk communication at the client device and receipt of the request by the push-to-talk server. The push-to-talk server transmits the audio recording to the one or more recipient devices. The push-to-talk server receives real-time audio from the client device. The push-to-talk server buffers the real-time audio for transmission to the one or more recipient devices after completion of playback of the audio recording.

Abstract: A push-to-talk server receives, while audio is being played back at a push-to-talk client device, one or more audio messages. The push-to-talk server stores the one or more audio messages in a buffer at the push-to-talk server in an order determined based at least in part on an initiation time of the one or more audio messages. The push-to-talk server determines, using an artificial intelligence engine and based on nonverbal features, an importance score for at least a portion of the one or more audio messages in the buffer. The push-to-talk server reorders the one or more audio messages based on the importance score. The push-to-talk server transmits the one or more audio messages for playback at the push-to-talk client device based on the order of the one or more audio messages.

Abstract: A push-to-talk client device receives a request to initiate an audio message. The push-to-talk client device records a first part of the audio message for storage in a buffer. The push-to-talk client device stores the first part in the buffer. The push-to-talk client receives, from a push-to-talk server, a confirmation that the push-to-talk server is receiving audio of the audio message from the push-to-talk client device. The push-to-talk client device transmits, to the push-to-talk server, the recorded first part of the audio message from the buffer. The push-to-talk client device transmits, to the push-to-talk server, real-time audio of the audio message.

Abstract: Identifying users who may be interested in content of a conference while the conference is ongoing includes generating a real-time transcript of a portion of the ongoing conference. The real-time transcript may be generated using a transcription engine accessing audio of an ongoing conference implemented by a conferencing software. Responsive to detecting that a topic-of-interest associated with a user who is not a current participant of the ongoing conference is referenced within the real-time transcript, a notification indicative of the topic-of-interest and the ongoing conference may be transmitted to a device associated with the user.

Abstract: A conference system transmits a first graphical output to display an indicator of a conference item on a display of a client device. Prior to the client device joining the conference, the conference system receives a request to view the conference item. The conference system transmits a second graphical output to the client device to display the conference item.

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 server generates a continuous audio stream during a real-time communication session. The server obtains a first audio stream from a user device connected to the real-time communication session and detects speech data in the first audio stream. The server converts the speech data to text data that includes one or more words. The server determines that the text data is missing a word based on a context of the one or more words. The server synthesizes a predicted word for replacing the missing word in a voice of a user of the user device and combines the synthesized word with the first audio stream to generate the continuous audio stream. The server transmits the continuous audio stream to other user devices connected to the real-time communication session.

Abstract: A shared device voicemail box can be accessed from a device that is an unauthenticated device without a user-specific security credential. The device transmits a request to a server. The request includes a unique code based on an image. The device accesses the voicemail box based on an access grant received from the server. Using the image, a non-registered user of a telephony system can access a secured voicemail box.

Abstract: A conference system transmits a first graphical output to display an indicator of a conference item on a display of a client device. Prior to the client device joining the conference, the conference system receives a request to view the conference item. The conference system transmits a second graphical output to the client device to display the conference item.

Abstract: A server generates a continuous audio stream during periods of poor network connectivity or network congestion. The server obtains a first audio stream from a user device connected to a real-time communication session and detects speech data in the first audio stream. The server converts the speech data to text data that includes one or more words. The server determines that the text data is missing a word based on a context of the one or more words. The server synthesizes a predicted word for replacing the missing word in a voice of a user of the user device and combines the synthesized word with the first audio stream to generate the continuous audio stream. The server transmits the continuous audio stream to other user devices connected to the real-time communication session.

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: 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, and the conference includes the user and other participants. A determination is made that the accent of the speech represented in the audio stream is different from the accents of the other participants. A user request to modify the accent of the speech is received from a device of one of the conference participants. The accent of the speech in the audio stream is modified to produce a modified audio stream. The modified audio stream is then caused to be output at the participant device from which the user request is received.

Abstract: Transformer-based message prioritization is performed to determine one or more messages for a user of a unified communications system to prioritize. A server of a unified communication system determines one or more intents of a user. The one or more intents are represented in natural language. A transformer engine of the server obtains a set of messages of the user. The transformer engine determines relevance scores for one or more messages of the set of messages based on the one or more intents and natural language information of the one or more messages. The server causes display of at least a subset of the set of messages based on the relevance scores.

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: A server generates a continuous audio stream during periods of poor network connectivity or network congestion. The server obtains a first audio stream from a user device connected to a real-time communication session and detects one or more missing packets in the first audio stream. The server obtains recorded portions of audio that correspond to the missing packets and combines the recorded portions of the audio with the first audio stream to generate the continuous audio stream without missing packets. The server transmits the continuous audio stream to other user devices connected to the real-time communication session.

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: Communications between participants of a video conference are accentuated based on a participant's focus. A first participant of a video conference is determined to be focused on a user interface element associated with a second participant of the video conference. Responsive to the determining that the first participant is focused on the user interface element associated with the second participant, relative audio levels of communications are changed for the second participant such that a first audio level for communications from the first participant to the second participant is higher than a second audio level for other communications received by the second participant.

Abstract: A shared device voicemail box can be accessed from a device that is an unauthenticated device without a user-specific security credential. The device transmits a request to a server. The request includes a unique code based on an image. The device accesses the voicemail box based on an access grant received from the server. Using the image, a non-registered user of a telephony system can access a secured voicemail box.