Abstract: Implementations for determining content perception by a participant in a media session by analyzing content are described. A content signal, such as an audio signal or a video signal, is received during a media session. A transcript of the content can be determined. Feedback, such as a pre-determined phrase, related to content perception by a participant in the media session is determined using a learning algorithm at the device. Metadata regarding the media session is collected in response to the feedback related to the content perception. The indication of the feedback related to the content perception and the metadata regarding the media session is then sent. In response, one or more adjustments to the media session are received. The one or more adjustments to the media session can be determined based on the indication of the feedback related to the content perception, the metadata regarding the media session, and network performance information.

Abstract: Implementations for selecting an input device based on characteristics of the input signals from those input devices are described. A first input signal is received from a first input device of a participant device participating in a media conference and a second input signal is received from a second input device of the participant device. A first characteristic of the first input signal and a second characteristic of the second input signal are determined. The first characteristic is compared to the second characteristic. It is determined that a quality of the second input signal is greater than a quality of the first input signal based on comparing the first characteristic to the second characteristic. The second input device is selected based on determining that the quality of the second input signal is greater than the quality of the first input signal.

Abstract: Implementations for metering media conferences based on active users are described. A plurality of media conferences are established by a media conferencing service. Unique users participating in the media conferences are determined. A number of times that each unique user uses the media conferencing service during a first time period is determined. A metric for use of the media conferencing service is determined based on the number of times that each unique user uses the media conferencing service. The metric for using the media conferencing service is output.

Abstract: A plurality of device-sharing participants may be detected that are participating in a videoconference via a shared computing device. The detecting of the plurality of device-sharing participants may be performed based, at least in part, on at least one of an audio analysis of captured audio from one or more microphones or a video analysis of captured video from one or more cameras. A plurality of participant connections corresponding to the plurality of device-sharing participants may be joined to the videoconference. Each of the plurality of participant connections may be identified within the videoconference using a respective name. A plurality of video streams and a plurality of audio streams corresponding to the plurality of participant connections may be transmitted, and the plurality of video streams and the plurality of audio streams may be presented to at least one other conference participant.

Abstract: A plurality of talker embedding vectors may be derived that correspond to a plurality of talkers in an input audio stream. Each talker embedding vector may represent respective voice characteristics of a respective talker. The talker embedding vectors may be generated based on, for example, a pre-enrollment process or a cluster-based embedding vector derivation process. A plurality of instances of a personalized noise suppression model may be executed on the input audio stream. Each instance of the personalized noise suppression model may employ a respective talker embedding vector. A plurality of single-talker audio streams may be generated by the plurality of instances of the personalized noise suppression model. A plurality of single-talker transcriptions may be generated based on the plurality of single-talker audio streams. The plurality of single-talker transcriptions may be merged into a multi-talker output transcription.

Abstract: A videoconference among a plurality of participants may be hosted, wherein the plurality of participants comprise Internet Protocol (IP)-connected participants and a Public Switched Telephone Network (PSTN)-connected participant. The IP-connected participants may send and receive audio content and video content of the videoconference via IP-based connections. The PSTN-connected participant may send and receive the audio content of the videoconference via a PSTN connection. Additional content from the videoconference may also be transmitted to the PSTN-connected participant, for example as text messages via the PSTN connection. The additional content may include, for example, images of a videoconference screen share, chat posts, polls, and the like. Images may be transmitted in the additional content based on video status change events, such as switching slides or pages in a screen share.

Abstract: Implementations for selecting hosting server(s) in a particular availability zone for a network service involving a plurality of participants is described. A request for a network service involving a plurality of nodes is received from a computing device associated with an organizer. Geographic locations of the plurality of nodes involved in the network service, the type of the network service, performance of a plurality of servers, and operational constraints of the plurality of servers are evaluated. At least two of the plurality of servers are located in different geographical locations. One or more of the plurality of servers to host the network service are selected based on the evaluation.

Abstract: This disclosure describes selecting the best hosting server(s) in a particular geographical location for the majority of participants in an interactive electronic activity. A request for an electronic interactive activity involving a plurality of nodes is received. At least one factor related to a plurality of potential servers is evaluated with respect to the plurality of nodes, where at least two of the plurality of potential servers are located in different geographical locations. Based at least in part on evaluating the factors, one or more of the potential servers is selected to host the electronic interactive activity, where the one or more of the potential servers selected are located in the same geographical location.

Abstract: This disclosure describes selecting the best hosting server(s) in a particular geographical location for the majority of participants in an interactive electronic activity. A request for an electronic interactive activity involving a plurality of nodes is received. At least one factor related to a plurality of potential servers is evaluated with respect to the plurality of nodes, where at least two of the plurality of potential servers are located in different geographical locations. Based at least in part on evaluating the factors, one or more of the potential servers is selected to host the electronic interactive activity, where the one or more of the potential servers selected are located in the same geographical location.

Abstract: Implementations for combining at least two video streams received from devices of a plurality of participants of a video conference into a composite video stream are described. A video conference including the video streams received from the devices of the plurality of participants is established. A capability associated with consuming at least two of the video streams is received from at least one of the devices. The at least two video streams are then combined into a composite video stream based on the capability associated with consuming the at least two video streams. The composite video stream is transmitted to the at least one of the devices.

Abstract: Implementations for selecting processing settings based on a device characteristic are described. A content signal, such as an audio signal or a video signal, is received. A characteristic of an input device and/or an output device is then determined and one or more processing settings for processing the content signal are determined based on the characteristic of the input device and/or the output device. The content signal is then processed based on the one or more settings and the processed content signal is sent for output. Feedback regarding the quality of the processed content signal is received. If the quality of the processed content signal is unacceptable, then one or more of the signal processing settings can be changed by deactivating a setting or changing a parameter of a setting.

Abstract: Implementations for combining a plurality of content based on instructions for a layout of a video conference are described. A video conference is established between a plurality of devices of participants of the video conference. First content is received from a device of the plurality of devices in the established video conference. Second content is also received. Instructions for a layout of the first content and the second content during the video conference is received. Based on the instructions for the layout, the first content and the second content are combined into a composite video stream. The composite video stream is saved or transmitted.

Abstract: A technology is described for providing virtual call assistants and call options to identified callers. An example method may include identifying a caller and a call recipient using addressing information included in a call received at a call control service. After identifying the caller, a priority designation assigned to the caller may be obtained from an agent linking profile. An interactive agent linked to the priority designation assigned to the caller may be identified, wherein the interactive agent may be configured to provide prioritized call services. Thereafter, the interactive agent linked to the priority designation may be invoked.

Abstract: Within environments, such as audio-video environments, users may synchronize output of multiple media source(s). To synchronize the output of the media source(s), users may define setting(s) associated with outputting the media source(s) at one or more devices. For example, the user may delay or accelerate the output of audio and/or video sources. Interfaces presented on one or more of the devices may allow the user to change the settings. For environments including multiple users, each user may define setting(s) associated with each user to synchronize output of their associated media source(s). Recommendations may be provided to users, that when implemented, attempt to synchronize the media sources.

Abstract: A service provider may determine that an electronic message sent from a first user device of a first user to a second user device of a second user includes a URL. The service provider may cause the URL to be unfurled, resulting in a preview of the URL, using a combination of a server-based process and a client-based process and one or more policies. Based on the policies, a cloud-based unfurling service may attempt to obtain metadata associated with the URL in order to unfurl the URL. If the server-based unfurling process is unable to unfurl the URL, the first device and/or the second device may obtain the metadata and unfurl the URL. As a result, the recipient of the message (e.g., the second user) may view an unfurled URL that includes a preview of a website corresponding to the URL (e.g., a title/headline, representative text, images, videos, etc.).

Abstract: A virtual meeting service receives a request from a participant through a computing device to join a virtual meeting. The request includes an identifier, which the virtual meeting service uses to identify one or more policies of the virtual meeting. The virtual meeting service, upon identifying these one or more policies, evaluates the one or more policies to determine whether to enable the computing device to be used to allow the participant to join the virtual meeting. If the virtual meeting service determines that the participant can join the virtual meeting, the virtual meeting service transmits a request to a telecommunications channel to connect the computing device to the virtual meeting, allowing the participant to join the virtual meeting.

Abstract: A computing device can be utilized to submit content to a collaboration service for posting on a collaboration channel. In response to receiving a posting request, the collaboration service identifies a context associated with the request. The context might include the location of the computing device submitting the request, the authenticated identity of the user submitting the request, or access rights associated with the content to be posted. The collaboration service can utilize the context to identify one or more collaboration channels to which the content can be posted. The user might be permitted to select one or more of the identified channels. Once the content has been posted to the selected channel, or channels, the collaboration service can utilize the context to perform other actions such as, but not limited to, initiating a communications session between authorized users of the collaboration channel to which the content was posted.

Abstract: Technologies for providing high performance geographically distributed data storage, retrieval and update are disclosed herein. In particular, a key/value storage service exposes a network service application programming interface (“API”) that includes create, update, retrieve, delete and configuration methods in some configurations. In order to implement the methods exposed by the API, the key/value storage service utilizes an in-memory cache service to store key/value pairs in an in-memory cache for highly performant retrieval. The key/value storage service also utilizes a distributed persistent storage service for storage of key/value pairs in a persistent backing store and for propagation of the key/value pairs to geographically distributed instances of the distributed persistent storage service.

Abstract: Described are techniques for establishing secure communication channels between user devices and service providing devices. Correspondence between a request received from a user device and security data may be used to determine that the user device has provided a valid access credential. The access credential may be replaced with a subsequent access credential after use. Correspondence between the request and service data may be used to determine that the request may be processed by the receiving service and that the user device has the permissions necessary for the request to be processed. Portions of the request that meet these criteria may be provided to the service. The secure communication channel may also be used to provide the response from the service to the user device.

Abstract: Described are techniques for determining an emergency event and associating label data with emergency communications to ensure that the emergency communications are provided with a greater quality and priority than non-emergency communications. When a quantity of communications associated with a network exceeds a threshold value, policy data may be generated and provided to network devices. The policy data may be configured to cause the network devices to transit communications associated with label data with high quality and connectivity. Correspondence between communications from the network and stored values indicative of emergency communications may be used to determine emergency communications from other data. Label data may be associated with the determined emergency communications to cause network devices to transit the communications in the manner indicated by the policy data.