Abstract: Delivering a transcribed voice message includes detecting receipt of a voice message for delivery to a user, the voice message related to an incoming call for the user; determining a current presence of the user on at least one of a plurality of messaging channels in real time during receipt of the voice message; transcribing the voice message to text in real time; and delivering, in real time, the transcribed voice message to the at least one messaging channel on which the current presence of the user is determined. Delivering the transcribed voice message can also include receiving from the user initial identification of different user accounts, along with authorizations and permissions.

Abstract: A method for manipulating voice attributes includes receiving, by a processor, a voice sample of a natural voice of a user, analyzing, by the processor, the voice sample for at least one attribute of the voice sample, receiving, by the processor, entered values for the at least one attribute of the voice sample and applying, by the processor, the entered values to the at least one attribute of the voice sample. The method further includes adjusting, by the processor, the at least one attribute of the voice sample based on the applied entered values to generate a manipulated voice sample, replacing, by the processor, the natural voice of the user with a modified voice of the user based on the manipulated voice sample and outputting, by the processor, the modified voice of the user.

Abstract: The technology disclosed herein enables user notification of word inconsistencies to indicate session quality. In a particular embodiment, a method includes, during a communication session between a first endpoint operated by a first participant and a second endpoint operated by a second participant, determining a first number of words spoken by the first participant during a period of time based on sound captured by the first endpoint for inclusion on the communication session. The method also includes determining a second number of the words spoken by the first participant during the period of time based on audio received at the second endpoint via the communication session. Upon determining that an inconsistency exists between the first number and the second number, the method includes notifying at least one of the first participant and the second participant about the inconsistency.

Abstract: Providing speech-to-text (STT) transcription by a user endpoint device includes initiating an audio communication between an enterprise server and the user endpoint device, the audio communication comprising a voice interaction between a user associated with the user endpoint device and an agent associated with an agent device to which the enterprise server routes the audio communication; performing a first STT of at least a portion of the voice interaction to produce a first transcribed speech in a first language; concurrent with performing the first STT, performing, by the user endpoint device, a second STT of the at least the portion of the voice interaction to produce a second transcribed speech in a second language different than the first language, and transmitting the at least the portion of the voice interaction and at least the first transcribed speech from the user endpoint device to the enterprise server.

Abstract: The present disclosure provides, among other things, methods and systems of managing communications, the method including: receiving a first communication; obtaining a user profile; comparing a user property from the user profile with a first content and a second content in the first communication; determining a first relevancy of the first content and a second relevancy of the second content; configuring a first content layout of the first communication based on the first relevancy and the second relevancy; and displaying the first content layout.

Abstract: The technology disclosed herein enables an absent participant to participate in a communication session. In a particular embodiment, a method includes identifying a meeting for an automated attendee to attend on behalf of a user. At a time for the meeting, the method includes joining the automated attendee to a communication session for the meeting. In the automated attendee, the method provides monitoring, in real-time, user communications exchanged between two or more other users over the communication session. During the monitoring, upon identifying a portion of the user communications that is relevant to the user, the method provides notifying the user about the portion.

Abstract: Customers can become bored with an interaction with an agent. By providing speech and/or images, of a celebrity disguising the speech, and/or image, of the agent, customers can appear to interact with a particular celebrity. As a result, customers are more likely to stay engaged and have a positive experience. The celebrity, or a particular persona of a celebrity, may be selected from customer preferences and/or a purpose of the call. For example, a movie star's role may have a persona, such as a “heavy,” suitable for collection calls (audio or audio-video), whereas a scientific or technical innovator may be selected for technical support calls.

Abstract: Systems and methods include generating an electronic calendar item associated with an event, generating an invitation associated with the electronic calendar item, the invitation comprising: a first option associated with one or more of conditional attendance and a portion of desired attendance; and a second option associated with one or more of a type of attendance; sending the invitation; receiving a response to the invitation, the response comprising a selection associated with one or more of the first option and the second option; and based on the selection, performing one or more actions associated with the event.

Abstract: Systems and methods include providing a recommendation for an attendance mode for a user to select when invited to an event through a calendaring application. Systems and methods include processing event and user data with a neural network configured to output a recommended attendance mode.

Abstract: The technology disclosed herein enables removal of extraneous voices from audio in a communication session. In a particular embodiment, a method includes receiving audio captured from an endpoint operated by a user on a communication session. The method further includes identifying an extraneous voice in the audio, wherein the voice is from a person other than the user, and removing the extraneous voice from the audio. After removing the extraneous voice, the method includes transmitting the audio to another endpoint on the communication session.

Abstract: Systems, methods, and software to provide intelligent detection and automatic correction of erroneous audio settings in a video conference. Electronic conferences can often be the source of frustration and wasted resources as participants may be forced to contend with extraneous sounds, such as background/ambient noises, or conversations not intended for the conference, provided by an endpoint that should be muted. Similarly, participants may speak with the intention of providing their speech to the conference while their associated endpoint is muted. As a result, the conference may be awkward and lack a productive flow while endpoints are erroneously muted or non-muted. By intelligently processing at least the video portion of a video conference, endpoints/participants may be prompted to mute/unmute or automatically muted/unmuted.

Abstract: The technology disclosed herein enables an indication of a post having been viewed to be presented across multiple instances of the post. In a particular embodiment, a method provides, in response to determining that a user has viewed a first instance of a post to an electronic communication channel, associating the post with a viewed-post status in a post-tracking repository. The method further provides identifying a second instance of the post and indicating to the user that the second instance has been viewed based on the post being associated with the viewed-post status.

Abstract: The present disclosure provides, among other things, methods and systems of managing communications, the methods and systems including: receiving a first group communication from a first group; determining, based on the first group communication, a first group sentiment; receiving a first communication with a request to send the first communication to the first group; determining, based on the first communication, a first communication sentiment; comparing the first group sentiment with the first communication sentiment; and based on the comparing, performing an action on the request to send the first communication.

Abstract: The technology disclosed herein enables an absent participant to participate in a communication session. In a particular embodiment, a method includes identifying a meeting for an automated attendee to attend on behalf of a user. At a time for the meeting, the method includes joining the automated attendee to a communication session for the meeting. In the automated attendee, the method provides monitoring, in real-time, user communications exchanged between two or more other users over the communication session. During the monitoring, upon identifying a portion of the user communications that is relevant to the user, the method provides notifying the user about the portion.

Abstract: Embodiments are directed to controlling playback of recordings. The recording can comprise an audio recording, audio/visual recording, voicemail message, or other recording having an audio component. According to one embodiment, a method can comprise capturing an audio recording of speech of at least one person and determining, a context for each of a plurality of portions of the audio recording based on natural language processing of the audio recording. One or more transition points between the portions of the audio recording can be identified. Each transition point can indicate a change in the determined context between the portions. A playback interface providing a representation of the audio recording and each of the identified transition points can be presented and the audio recording can be played based on input received through the playback interface.

Abstract: Electronic conferences can often be the source of frustration and wasted resources as participants may be forced to contend with extraneous sounds, such as conversations not intended for the conference, provided by an endpoint that should be muted. Similarly, participants may speak with the intention of providing their speech to the conference but speak while their associated endpoint is muted. As a result, the conference may be awkward and lack a productive flow while erroneously muted or non-muted endpoints are addressed. By detecting erroneous audio settings, endpoints can be prompted or automatically corrected to have the appropriate audio state.

Abstract: Video conferencing systems are popular means for remote parties to interact in real-time. A user may wish to emphasize certain visual elements of the video conference, for example, a company's logo or the contents of a whiteboard may be important to remain clearly seen by the viewers of the video conference. As elements are obscured, a previously captured image of the obscured visual element may be overlaid on top of the obscuring image to visual remove the obscuring object. Additionally, certain visual elements may be enhanced, such that a small visual element may appear larger or clearer within the video image.

Abstract: Systems and methods include providing a recommendation for an attendance mode for a user to select when invited to an event through a calendaring application. Systems and methods include processing event and user data with a neural network configured to output a recommended attendance mode.

Abstract: A device may analyze the content of a communication input via the device and verify a recipient associated with the communication based on the analysis. A machine learning network associated with the device may analyze the content and generate a probability score and a confidence score indicating an association between the communication and the recipient. Based on the probability score or confidence score provided by the machine learning network, the device may verify whether the content of the communication matches profile information associated with the recipient. In some cases, the device may refrain from transmitting the message to the recipient or output a notification suggesting a different recipient for the message. The device may output a notification to modify content of the communication, modify recipients for the communication, select a different messaging window for the communication, or select a different application for the communication.

Abstract: Systems and methods include generating an electronic calendar item associated with an event, generating an invitation associated with the electronic calendar item, the invitation comprising: a first option associated with one or more of conditional attendance and a portion of desired attendance; and a second option associated with one or more of a type of attendance; sending the invitation; receiving a response to the invitation, the response comprising a selection associated with one or more of the first option and the second option; and based on the selection, performing one or more actions associated with the event.