Abstract: A system and method for automatically connecting an accessory with a host device are disclosed. The accessory may include a private key and a public key, wherein the public key is associated with an account. The same account may be associated with the host device. The accessory may transmit an encrypted message, including a key, to the host device, wherein the key may be the public key. Upon decryption and validation of the key, the accessory and host device may automatically connect via short-range wireless pairing.

Abstract: Mechanisms for controlling an audio level of an HDMI audio system are provided, the mechanisms comprising: causing audio data to be presented by an HDMI audio system at a current system volume level; receiving a requested volume level from a second screen device; and controlling a system volume level by: (a) determining the current system volume level; (b) determining a change in volume based on a difference between the requested volume level and the current system volume level; (c) determining a direction in which to cause the system volume level to change; (d) sending a volume control message to the system using a consumer electronic control bus connected to the system indicating whether to increase or decrease the system volume level based on the determined direction of system volume change; and (e) repeating (a)-(d) until the current system volume level reaches a predetermined value.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for allocating cache resources according to page-level attribute values. In one implementation, the system includes one or more integrated client devices and a cache. Each client device is configured to generate at least a memory request. Each memory request has a respective physical address and a respective page descriptor of a page to which the physical address belongs. The cache is configured to cache memory requests for each of the one or more integrated client devices. The cache comprises a cache memory having multiple ways. The cache is configured to distinguish different memory requests using page-level attributes of respective page descriptors of the memory requests, and to allocate different portions of the cache memory to different respective memory requests.

Abstract: Systems, methods, and media for obfuscated personal identification number entry on media devices are provided.

Abstract: A method for training a streaming automatic speech recognition student model includes receiving a plurality of unlabeled student training utterances. The method also includes, for each unlabeled student training utterance, generating a transcription corresponding to the respective unlabeled student training utterance using a plurality of non-streaming automated speech recognition (ASR) teacher models. The method further includes distilling a streaming ASR student model from the plurality of non-streaming ASR teacher models by training the streaming ASR student model using the plurality of unlabeled student training utterances paired with the corresponding transcriptions generated by the plurality of non-streaming ASR teacher models.

Abstract: This document generally describes systems and methods for dynamically adapting speech recognition for individual voice queries of a user using class-based language models. The method may include receiving a voice query from a user that includes audio data corresponding to an utterance of the user, and context data associated with the user. One or more class models are then generated that collectively identify a first set of terms determined based on the context data, and a respective class to which the respective term is assigned for each respective term in the first set of terms. A language model that includes a residual unigram may then be accessed and processed for each respective class to insert a respective class symbol at each instance of the residual unigram that occurs within the language model. A transcription of the utterance of the user is then generated using the modified language model.

Abstract: A device may include a rectifier circuit providing a rectified DC signal, a rechargeable energy-storage element, and a power-management integrated circuit (PMIC). The PMIC may include a charging circuit for the rechargeable energy-storage element; a current-sensing circuit that measures a current provided by the rectified DC signal; a programmable current limit; a voltage-sensing circuit that measures a voltage on the rechargeable energy-storage element; and a controller that regulates the current provided to a DC output of the PMIC. the DC output of the PMIC may be regulated based at least in part on the current provided by the rectified DC signal; the programmable current limit; and the voltage on the rechargeable energy-storage element. The DC output of the PMIC may provide energy to a plurality of other energy-consuming subsystems on the device and to the charging circuit for the rechargeable energy-storage element.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a text summarization neural network.

Abstract: Methods and systems for verbal polling during a conference call discussion are provided. A graphical user interface (UI) is provided to participants of a video conference call. The UI enables one of the participants to verbally provide a question for polling of one or more additional participants of the participants. An indication that a first participant is to provide a verbal question is received via the UI. The verbal question provided by the first participant is recorded. An indication that the first participant has finished providing the verbal question is received via the UI. A determination is made that the verbal question is to be used for polling of second participants of the video conference call. A textual form of the verbal question is provided to the one or more second participants of the video conference call in the UI.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting a neural network to perform a particular machine learning task while satisfying a set of constraints.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, at a mobile computing device that is associated with a called user, a call from a calling computing device that is associated with a calling user; in response to receiving the call, determining, by the mobile computing device, that data associated with the called user indicates that the called user will not respond to the call; in response to determining that the called user will not respond to the call, inferring, by the mobile computing device, an informational need of the calling user; and automatically providing, from the mobile computing device to the calling computing device, information associated with the called user and that satisfies the inferred informational need of the calling user.

Abstract: An electronic device receives a first plurality of images of a scene captured by an image sensor of an electronic device, receives an ambient light level proximate to the electronic device, and determines whether the ambient light level is less than a first threshold value. In accordance with a determination that the ambient light level is less than the first threshold value, the electronic device detects motion in the scene based on one or more of the first plurality of images. In accordance with detecting motion in the scene, the electronic device receives a second plurality of images of the scene captured by the image sensor of the electronic device, forms a composite image from two or more of the second plurality of images, and causes the composite image to be presented for display on a user device.

Abstract: This document describes methods and systems for user equipment (UE) context transfer over radio access network (RAN) paging. A first base station receives from a second base station a first message that includes a context that is associated with a user equipment while the user equipment was in an engaged mode with the second base station. The first base station transmits a second message that is a paging message to the user equipment and in response receives, from the user equipment, a third message that includes a resume message authentication code identifier. After the first base station verifies the third message using the resume message authentication code identifier, the first base station transmits, to the user equipment, a fourth message that enables the user equipment to resume the engaged mode with the first base station in accordance with the context.

Abstract: This document describes methods, devices, systems, and means for enhanced beam searching for an active coordination set. A user equipment (110) receives an active-coordination-set beam-sweep (602) including multiple time slots (610), each of the multiple time slots including one or more candidate beams. The user equipment (110) determines a respective link-quality metric for each of the received one or more candidate beams in each of the time slots. Based on the link-quality metrics, the user equipment (110) selects the one or more candidate beams in a time slot (610) to use for wireless communication. The user equipment (110) transmits a beam-acquired indication (620) at a first time offset (604) after the time slot (610) in which the selected one or more candidate beams are received, the transmitting directing the base stations (120) to use the selected one or more candidate beams for the wireless communication.

Abstract: Techniques and apparatuses are described that enable memory request timeouts using a common counter. A memory request is received, and a common count timeout is generated for the memory request based on a common count at a time of receipt and a latency requirement of the memory request. Common count timeouts of one or more related memory requests within a memory request buffer (if they exist) are adjusted as needed, and the memory request is placed in the memory request buffer. The common count is incremented, and the memory request is indicated as timed out in response to an incrementation of the common count matching the common count timeout for the memory request.

Abstract: A method for data storage includes specifying a plurality of File Systems (FSs) for use by multiple clients, including assigning to the FSs both respective global identifiers and respective client-specific names. The plurality of FSs is managed using the global identifiers, and files are stored for the clients in the FSs using the client-specific names.

Abstract: A joint segmenting and ASR model includes an encoder and decoder. The encoder configured to: receive a sequence of acoustic frames characterizing one or more utterances; and generate, at each output step, a higher order feature representation for a corresponding acoustic frame. The decoder configured to: receive the higher order feature representation and generate, at each output step: a probability distribution over possible speech recognition hypotheses, and an indication of whether the corresponding output step corresponds to an end of speech segment. The j oint segmenting and ASR model trained on a set of training samples, each training sample including: audio data characterizing a spoken utterance; and a corresponding transcription of the spoken utterance, the corresponding transcription having an end of speech segment ground truth token inserted into the corresponding transcription automatically based on a set of heuristic-based rules and exceptions applied to the training sample.

Abstract: This application is directed to a doorbell camera for illuminating and capturing scenes. The doorbell camera includes at least a subset of processors for operating a camera module, an image sensor having a field of view of a scene and configured to capture video of a portion of the scene, one or more infrared (IR) illuminators for providing illumination, a waterproof button assembly, and a microphone and a speaker for enabling a real-time conversation between a visitor located at the doorbell camera and a user of a remote client device. The waterproof button assembly is configured to receive a user press on a button top, block water from entering the electronic device, and display a visual pattern uniformly at a peripheral region of the button assembly using LEDs and light guide component that are disposed under the button top.