Abstract: One embodiment of the present invention sets forth a technique for processing recordings of events. The technique includes applying a machine learning model to a plurality of samples from one or more recordings of the events to generate a plurality of embeddings representing the plurality of samples. The technique also includes generating a plurality of labels that identify speakers associated with the plurality of samples based on metadata comprising timestamps of voice activity during the events and participants associated with the voice activity. The technique further includes storing mappings of the plurality of embeddings to the plurality of labels.

Abstract: One embodiment of the present invention sets forth a technique for processing recordings of events. The technique includes applying a machine learning model to a plurality of samples from one or more recordings of the events to generate a plurality of embeddings representing the plurality of samples. The technique also includes generating a plurality of labels that identify speakers associated with the plurality of samples based on metadata comprising timestamps of voice activity during the events and participants associated with the voice activity. The technique further includes storing mappings of the plurality of embeddings to the plurality of labels.

Abstract: One embodiment of the present invention sets forth a technique for processing recordings of events. The technique includes applying a machine learning model to a plurality of samples from one or more recordings of the events to generate a plurality of embeddings representing the plurality of samples. The technique also includes generating a plurality of labels that identify speakers associated with the plurality of samples based on metadata comprising timestamps of voice activity during the events and participants associated with the voice activity. The technique further includes storing mappings of the plurality of embeddings to the plurality of labels.

Abstract: One embodiment of the present invention sets forth a technique for processing recordings of events. The technique includes applying a machine learning model to a plurality of samples from one or more recordings of the events to generate a plurality of embeddings representing the plurality of samples. The technique also includes generating a plurality of labels that identify speakers associated with the plurality of samples based on metadata comprising timestamps of voice activity during the events and participants associated with the voice activity. The technique further includes storing mappings of the plurality of embeddings to the plurality of labels.

Abstract: One embodiment of the present invention sets forth a technique for enhancing meeting participation by an interactive virtual assistant. The technique includes loading a resource for conducting the meeting over a teleconferencing system. The technique also includes configuring, based on the resource, virtual input/output (I/O) devices for integrating the interactive virtual assistant into the teleconferencing system during the meeting. In response to a command received over a first device in the virtual I/O devices, the technique further includes generating, by the interactive virtual assistant, output containing a response to the command over a second device in the virtual I/O devices.

Abstract: One embodiment of the present invention sets forth a technique for processing recordings of events. The technique includes applying a machine learning model to a plurality of samples from one or more recordings of the events to generate a plurality of embeddings representing the plurality of samples. The technique also includes generating a plurality of labels that identify speakers associated with the plurality of samples based on metadata comprising timestamps of voice activity during the events and participants associated with the voice activity. The technique further includes storing mappings of the plurality of embeddings to the plurality of labels.

Abstract: One embodiment of the present invention sets forth a technique for enhancing meeting participation by an interactive virtual assistant. The technique includes loading a resource for conducting the meeting over a teleconferencing system. The technique also includes configuring, based on the resource, virtual input/output (I/O) devices for integrating the interactive virtual assistant into the teleconferencing system during the meeting. In response to a command received over a first device in the virtual I/O devices, the technique further includes generating, by the interactive virtual assistant, output containing a response to the command over a second device in the virtual I/O devices.

Abstract: Implementations of the present disclosure provide systems and methods for seamlessly transferring a communication session from a first client to a second client via a close-range communication connection. Implementations contemplate serializing a set of unique identifiers pertaining to a communication session and transmitting the set of serialized identifiers from the first client to the second client via a close-range communication connection. The second client de-serializes the set of unique identifiers and transmits a request to a communication session server to assume control of the communication session from the first client. A communication session server may perform an authentication of the second client that requires the second client to provide credentials associated with a user account. In some implementations, the present disclosure provides for the creation of a temporary use token that enables a client to temporarily acquire credentials associated with a user account.

Abstract: Content such as a television program can be shared by pushing a content identifier to a queue through a social network. A share request from a sender can designate a recipient for the content. An implementation can determine if the sender and the recipient have permission to share the content. If permitted, an identifier associated with the content can be pushed to a viewing queue of the recipient. A user can subscribe to follow a viewing queue, which can provide to the user access to the queue's listing of content, as well as the content itself.

Abstract: Implementations of the present disclosure provide systems and methods for seamlessly transferring a communication session from a first client to a second client via a close-range communication connection. Implementations contemplate serializing a set of unique identifiers pertaining to a communication session and transmitting the set of serialized identifiers from the first client to the second client via a close-range communication connection. The second client de-serializes the set of unique identifiers and transmits a request to a communication session server to assume control of the communication session from the first client. A communication session server may perform an authentication of the second client that requires the second client to provide credentials associated with a user account. In some implementations, the present disclosure provides for the creation of a temporary use token that enables a client to temporarily acquire credentials associated with a user account.

Abstract: Certain implementations of the disclosed technology may include systems and methods for computing device communications. According to an example implementation of the disclosed technology, a method is provided that can include determining a status and capability of at least one selected computing device, and sending a generated message to the at least one selected computing device. The at least one selected computing device is configured to retrieve content from a source identified by a uniform resource identifier in the message, and the at least one selected computing device is further configured to present the retrieved content.

Abstract: Certain implementations of the disclosed technology may include systems and methods for computing device communications. According to an example implementation of the disclosed technology, a method is provided that can include determining a status and capability of at least one selected computing device, and sending a generated message to the at least one selected computing device. The at least one selected computing device is configured to retrieve content from a source identified by a uniform resource identifier in the message, and the at least one selected computing device is further configured to present the retrieved content.