Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a central device may transmit a first communication to initiate a first communication event. The central device may transmit a first synchronization message associated with a first peripheral device and a second synchronization message associated with a second peripheral device during a first time resource and a second time resource, respectively, associated with a first communication event. The central device may transmit a second communication to initiate a second communication event. The central device may monitor, during the second communication event, for a first response from the first peripheral device during a third time resource, and for a second response from the second peripheral device during a fourth time resource. Numerous other aspects are described.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. Voice data from a first user is received. In response to determining that the voice data includes an utterance of a defined keyword, a user verification score is generated by processing the voice data using a first user verification machine learning (ML) model, and a quality of the voice data is determined. In response to determining that the user verification score and determined quality satisfy one or more defined criteria, a second user verification ML model is updated based on the voice data.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for a training and using machine learning models in multi-device network environments. An example computer-implemented method for network communications performed by a host device includes extracting a feature set from a data set associated with a client device using a client-device-specific feature extractor, wherein the feature set comprises a subset of features in a common feature space, training a task-specific model based on the extracted feature set and one or more other feature sets associated with other client devices, wherein the feature sets associated with the other client devices comprise one or more subsets of features in the common feature space, and deploying, to each respective client device of a plurality of client devices, a respective version of the task-specific model.

Abstract: Systems and techniques are provided for processing audio data. For instance, a process can include detecting a first audio data between two or more in-person participants of a plurality of in-person participants of a group communication session. The first audio data can be identified as private based on one or more cues associated with the first audio data. A second audio data can be identified between the two or more in-person participants. The second audio data can be identified as non-private based on one or more additional cues associated with the second audio data, wherein the one or more additional cues associated with the second audio data are different from the one or more cues associated with the first audio data. The second audio data can be output based on identifying the second audio data as non-private.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a first peripheral device may establish, with a user equipment (UE), a first connected isochronous stream (CIS), a second CIS, and a control channel for the first CIS and the second CIS, where the first peripheral device is configured to output audio signals for the first CIS and handle feedback for the first CIS. The first peripheral device may transmit, to a second peripheral device paired with the first peripheral device, an indication that the second peripheral device is to output audio signals for the second CIS and handle feedback for the second CIS. The first peripheral device may receive the first CIS, while maintaining the control channel for the first CIS and the second CIS. Numerous other aspects are described.

Abstract: Systems and techniques are provided for processing audio data. For instance, a process can include obtaining a primary audio signal from a user computing device and obtaining first audio data from an additional computing device, wherein the additional computing device is within an auditory range of the user computing device. The primary audio signal can be filtered to generate a filtered primary audio signal. The filtering can include removing a representation of the first audio data from the primary audio signal. The filtered primary audio signal can be output to a network-based meeting.

Abstract: Described are techniques for sharing data among a group of mobile devices that are registered to the same user. In some instances, the shared data is sensor data captured by a mobile device or media content being processed by the mobile device. The mobile devices in the group are configured to wirelessly communicate with each other and to share status information. Using the status information, the mobile devices can keep each other updated as to the operational status of each individual mobile device and, in some aspects, the status of a mobile device with respect to the user. The sensor data or media content can be forwarded to a different mobile device in response to a determination made based on the status information. For instance, forwarding can be based on a rule that specifies one or more conditions relating to the status of a mobile device and/or user status.

Abstract: Disclosed are techniques for wireless communication. In an aspect, a controller wireless device establishes a wireless communication link with a remote wireless device according to a configuration profile for a wireless communications standard, receives, from the remote wireless device, a first request to increase a transmit power level of the controller wireless device, determines whether a signal strength metric for the wireless communication link is below a first signal strength threshold, whether a reliability metric for the wireless communication link is below a first reliability threshold, or both, and based on the signal strength metric being below the first signal strength threshold, the reliability metric being below the first reliability threshold, or both, increases the transmit power level of the controller wireless device.

Abstract: Systems and techniques are provided for processing audio data. For instance, a process can include detecting a first audio data between two or more in-person participants of a plurality of in-person participants of a group communication session. The first audio data can be identified as private based on one or more cues associated with the first audio data. A second audio data can be identified between the two or more in-person participants. The second audio data can be identified as non-private based on one or more additional cues associated with the second audio data, wherein the one or more additional cues associated with the second audio data are different from the one or more cues associated with the first audio data. The second audio data can be output based on identifying the second audio data as non-private.

Abstract: Various aspects include methods for supporting context broadcast networking by a device. Aspects provide a cross ecosystem platform that enable seamless user experiences from device centric and fragmented user experiences. Some aspects may include decrypting a broadcast message received from a radio controller if the received broadcast message indicates an account identity value matching a pre-calculated account identity value and is not a duplicate, generating data elements from the decrypted broadcast message, storing the data elements in a data cache; and signaling an interrupt indicating that the data elements are available. Further aspects include a radio controller receiving a first scan interval from a primary host and a second scan interval from a secondary host of the device; scheduling primary host scan windows based on the first scan interval, and cancelling any secondary host second scan windows overlapping any of the scheduled primary host first scan windows.

Abstract: This disclosure describes a first slave device that transmits information to a second slave device indicating that a first data packet was improperly received from a master device, so that a corresponding data packet may be relayed from the second slave device to the first slave device. In an aspect, the second slave device may receive a first data packet followed by an indication that the first slave device improperly received the first data packet, where the second slave device is configured to relay the first data packet to the first slave device in response thereto. In another aspect, the second slave device may receive a request to listen for a separate data stream of the first slave device based on a first data packet being improperly received by the first slave device and transmit a second data packet of the separate data stream to the first slave device.

Abstract: Described are techniques for sharing data among a group of mobile devices that are registered to the same user. In some instances, the shared data is sensor data captured by a mobile device or media content being processed by the mobile device. The mobile devices in the group are configured to wirelessly communicate with each other and to share status information. Using the status information, the mobile devices can keep each other updated as to the operational status of each individual mobile device and, in some aspects, the status of a mobile device with respect to the user. The sensor data or media content can be forwarded to a different mobile device in response to a determination made based on the status information. For instance, forwarding can be based on a rule that specifies one or more conditions relating to the status of a mobile device and/or user status.

Abstract: A device includes a memory configured to store instructions and one or more processors configured to execute the instructions. The one or more processors are configured to execute the instructions to obtain link data corresponding to a communication link to a second device. The one or more processors are configured to execute the instructions to select, at least partially based on the link data, between an ambisonics mode and a stereo mode.

Abstract: A device includes a memory configured to store instructions and one or more processors configured to execute the instructions to receive a media packet and to determine, based on a field of the media packet, whether the media packet includes motion data. The one or more processors are also configured to execute the instructions to, based on the media packet including motion data, extract the motion data from the media packet.

Abstract: Devices and methods for connected isochronous stream (CIS) swapping are disclosed. In an example Bluetooth™ setting, a smartphone can be connected to multiple earbuds. It is possible that both earbuds include microphones, but only one microphone is enabled at a given time. That is, only one of the CISes established between the smartphone and the earbuds is bidirectional, and the other is unidirectional. The disclosed techniques enable the CISes to be swapped between the earbuds so that the earbud with better microphone quality will have ownership of the bidirectional CIS.

Abstract: Reduced Advanced Audio Distribution Profile (A2DP) latency on a link between a source and a pair of headphones may be achieved by improving the quality of the link between secondary and primary and establishing a direct link between the source and secondary to mitigate the link quality issues of the source and primary link. In one example, this involves receiving, via a first receiver, packets from a source on a first wireless connection, determining, by the first receiver, that a first packet received via the first wireless connection has an error, establishing a second connection between the first receiver and a second receiver, and establishing a third connection between the second receiver and the source. In particular, the first receiver may be configured as a primary True Wireless Stereo (TWS) Bluetooth device and the second receiver may be configured as a secondary TWS Bluetooth device.

Abstract: The present disclosure provides a mechanism to perform a CSB burst mode between a master device and one or more slave devices. In CSB burst mode, the master device may broadcast more than one packet of data in a CSB interval, and hence, may use the time slots in a CSB interval more efficiently than while operating in traditional CSB mode. CSB burst mode of the present disclosure may be used to improve the latency and duty cycle of data transmissions, such as for example, broadcast audio. In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may determine to broadcast a set of packets during a CSB interval, where the set of packets includes a plurality of packets. In some aspects, the apparatus may broadcast the set of packets during the CSB interval to a set of second nodes.

Abstract: In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. In certain configurations, the apparatus may connect to a mesh network that includes at least the first device and a second device. The apparatus may communicate with the second device without obtaining one or more access credentials from the second device.

Abstract: A wireless device is provided that determines a set of expected packets from a second wireless device, each expected packet of the set of expected packets comprising an expected cyclic redundancy check (CRC) of a set of expected CRCs, receives a packet from the second wireless device, the received packet comprising a header and a first CRC, determines whether a second CRC generated based on the header in the received packet matches the first CRC received in the received packet, determines, when the generated second CRC does not match the first CRC received in the received packet, a third CRC of the set of expected CRCs based on the first CRC, and replaces the received header with a header corresponding to the determined third CRC.

Abstract: Reduced Advanced Audio Distribution Profile (A2DP) latency on a link between a source and a pair of headphones may be achieved by improving the quality of the link between secondary and primary and establishing a direct link between the source and secondary to mitigate the link quality issues of the source and primary link. In one example, this involves receiving, via a first receiver, packets from a source on a first wireless connection, determining, by the first receiver, that a first packet received via the first wireless connection has an error, establishing a second connection between the first receiver and a second receiver, and establishing a third connection between the second receiver and the source. In particular, the first receiver may be configured as a primary True Wireless Stereo (TWS) Bluetooth device and the second receiver may be configured as a secondary TWS Bluetooth device.