Abstract: Apparatus and methods related to applying lighting models to images of objects are provided. A neural network can be trained to apply a lighting model to an input image. The training of the neural network can utilize confidence learning that is based on light predictions and prediction confidence values associated with lighting of the input image. A computing device can receive an input image of an object and data about a particular lighting model to be applied to the input image. The computing device can determine an output image of the object by using the trained neural network to apply the particular lighting model to the input image of the object.

Abstract: Systems and methods for providing online content include evaluating a custom selection rule specified by a content provider. The custom selection rule may be used to control whether content from the provider is eligible for selection by a content selection service. The content selection rule may include one or more logical operators, a selected interest category and/or a selected list of one or more client identifiers.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for hotword trigger suppression are disclosed. In one aspect, a method includes the actions of receiving, by a microphone of a computing device, audio corresponding to playback of an item of media content, the audio including an utterance of a predefined hotword that is associated with performing an operation on the computing device. The actions further include processing the audio. The actions further include in response to processing the audio, suppressing performance of the operation on the computing device.

Abstract: The subject matter of the present disclosure can be implemented in, among other things a computer-readable storage medium encoded with instructions for causing a programmable processor to receive, by a server, a first message from a remote control that is distinct from and external to the server, wherein the first message includes a remote control identifier and control information for controlling one or more functions of at least one device other than the remote control. The instructions also cause the programmable processor to retrieve, by the server, a controlled device identifier that uniquely identifies a controlled device that is distinct from and external to the server. The instructions also cause the programmable processor to send a second message from the server to the controlled device identified by the controlled device identifier to control an operation of the controlled device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using a priority queue. One of the methods includes maintaining data identifying a set of K output sequences that were previously generated; selecting at least one of the output sequences from the set of output sequences; for each selected output sequence, determining a respective score; determining, for each selected sequence, a respective first update to the current values of the controller parameters; generating a batch of new output sequences using the controller neural network; obtaining a respective reward for each of the new output sequences; determining, from the new output sequences and the output sequences in the maintained data, the K output sequences that have the highest rewards; and modifying the maintained data.

Abstract: A Bluetooth device controlling a plurality of wireless audio devices, includes: a wireless communication circuit, to receive a wireless audio device identifier from each wireless audio device; a sound processing circuit to apply independent audio effects on a main audio stream such that the sound processing circuit outputs as many modified audio streams as the wireless communication circuit has received identifiers of wireless audio devices, on the basis of the characteristics of each wireless audio device; an allocation circuit to allocate each modified audio stream to a respective wireless audio device; and a transmission circuit to wirelessly transmit through a Bluetooth usage each modified audio stream to the respective wireless audio device for emission by the wireless audio devices.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for suppressing hotword triggers when detecting a hotword in recorded media are disclosed. In one aspect, a method includes the actions of receiving, by a computing device, audio corresponding to playback of an item of media content. The actions further include determining, by the computing device, that the audio includes an utterance of a predefined hotword and that the audio includes an audio watermark. The actions further include analyzing, by the computing device, the audio watermark. The actions further include based on analyzing the audio watermark, determining, by the computing device, whether to perform speech recognition on a portion of the audio following the predefined hotword.

Abstract: Implementations described herein relate to methods, devices, and computer-readable media to transcode a video. In some implementations, a computer-implemented method includes obtaining a video that includes a plurality of tracks. The method further includes determining whether a partial transcoded file is available that corresponds to the video. The method further includes, if the partial transcoded file is available, obtaining a timestamp associated with the partial transcoded file, transcoding a portion of the video that begins at the timestamp associated with the partial transcoded file, and combining the partial transcoded file and the transcoded portion of the video to generate an output video. The method further includes, if the partial transcoded file is not available, transcoding the video from a start of the video using the transcoder to obtain a plurality of output tracks and combining the plurality of output tracks to obtain the output video.

Abstract: Systems and methods are provided for displaying and interacting with multiple open views in a mobile environment. An example method can include displaying content for a first web page in a first pane in a maximized state on a mobile device, receiving a touch input on a navigation control associated with the first pane, and responsive to receiving the touch input, displaying a second web page in a second pane on the mobile device, the second pane being in a minimized state in a dock area. The dock area can overlay the first pane in the maximized state and the minimized state of the second pane can display a smaller version of the second web page than the second pane in a maximized state. In some examples the second web page updates content in parallel with the first web page.

Abstract: Data content governance for presentation layer synchronization for a version controlled underlying data model includes defining a data model for underlying data in a database, specifying a presentation layer for the defined data model and identifying selected elements of the data model necessary to meet data requirements of the specified presentation layer. Then, the identified selected elements of the data model are serialized and both the specified presentation layer and the serialized elements are versioned in respect to the specified presentation layer. Thereafter, when the data model becomes modified, the specified presentation layer is modified to accommodate the modified data model. In response to the modification, a different selection of elements of the data model necessary to meet data requirements of the modified presentation layer are re-identified and serialized, with the modified presentation layer and the serialized re-identified different selection of elements becoming re-versioned.

Abstract: A circuit is presented which includes a first amplifier having an input, a transmission line having first and second ends. The first end of the transmission line is coupled to an input of the first amplifier and a plurality of channels. Each channel includes a plurality of resonators arranged to read out a plurality of qubits, respectively and a readout line arranged to receive read out signals from the plurality of resonators. The readout line of each channel is coupled to the transmission line and each channel is configured to output a respective signal in a respective frequency band which is different from frequency bands of other channels in the plurality of channels.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice input from a user device; generating a first recognition output; receiving a user selection of one or more terms in the first recognition output; receiving a second voice input spelling a correction of the user selection; determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.

Abstract: A device may identify a plurality of sources for outputs that the device is configured to provide. The plurality of sources may include at least one of a particular application in the device, an operating system of the device, a particular area within a display of the device, or a particular graphical user interface object. The device may also assign a set of distinct voices to respective sources of the plurality of sources. The device may also receive a request for speech output. The device may also select a particular source that is associated with the requested speech output. The device may also generate speech having particular voice characteristics of a particular voice assigned to the particular source.

Abstract: A method includes receiving, from a speech recognizer, multiple existing candidate hypotheses for an utterance. Each existing candidate hypothesis has a corresponding likelihood score assigned by the speech recognizer. The method also includes generating, using a correction module configured to receive the multiple candidate hypotheses as input, a new candidate hypothesis and determining, using a comparison model configured to receive the corresponding likelihood score assigned to one of the multiple existing candidate hypotheses as input, a corresponding likelihood score. The method also includes ranking the multiple existing candidate hypotheses and the new candidate hypothesis based on the corresponding likelihood scores assigned to the multiple existing candidate hypothesis by the speech recognizer and the corresponding likelihood score for the new candidate hypothesis.

Abstract: Various arrangements for monitoring for contactless human interactions and health using a single radar transmission modulation mode are provided. Radar chirps may be output by a radar sensor operating in a burst mode. The burst mode radar data stream may be monitored for a contactless human interaction performed by an active user. The burst mode radar data stream may be converted to a virtual continuous mode radar data stream. Health monitoring of an inactive user may be performed using the virtual continuous mode radar data stream.

Abstract: A method for generating frame values using a key frame network includes receiving a text utterance having at least one phoneme, and for each respective phoneme of the at least one phoneme, predicting, using a predictive model, a fixed quantity of key frames. Each respective key frame of the fixed quantity of key frames includes a representation of a component of the respective phoneme. The method also includes generating, using the fixed quantity of key frames, a plurality of frame values. Here, each respective frame value of the plurality of frame values is representative of a fixed-duration of audio.

Abstract: A method includes receiving, as input to a speech recognition model, audio data corresponding to a spoken utterance. The method also includes performing, using the speech recognition model, speech recognition on the audio data by, at each of a plurality of time steps, encoding, using an audio encoder, the audio data corresponding to the spoken utterance into a corresponding audio encoding, and decoding, using a speech recognition joint network, the corresponding audio encoding into a probability distribution over possible output labels. At each of the plurality of time steps, the method also includes determining, using an intended query (IQ) joint network configured to receive a label history representation associated with a sequence of non-blank symbols output by a final softmax layer, an intended query decision indicating whether or not the spoken utterance includes a query intended for a digital assistant.

Abstract: A method includes inserting a set of canary text samples into a corpus of training text samples and training an external language model on the corpus of training text samples and the set of canary text samples inserted into the corpus of training text samples. For each canary text sample, the method also includes generating a corresponding synthetic speech utterance and generating an initial transcription for the corresponding synthetic speech utterance. The method also includes rescoring the initial transcription generated for each corresponding synthetic speech utterance using the external language model. The method also includes determining a word error rate (WER) of the external language model based on the rescored initial transcriptions and the canary text samples and detecting memorization of the canary text samples by the external language model based on the WER of the external language model.

Abstract: Techniques and devices for expressing multicast groups using Weave traits are described for generating a multicast address in which a wireless network device receives an application group identifier and hashes the application group identifier to generate a group identifier. The wireless network device concatenates a global identifier and a Weave fabric identifier, inserts the concatenated global identifier and the Weave fabric identifier into a network prefix field of a destination address, and inserts the group identifier into a group identifier field of the destination address. The wireless network device sets the value of a plen field of the destination address to a value that indicates a length of the Weave fabric identifier and inserts the destination address into an Internet Protocol version 6 data packet.

Abstract: This application is directed to a battery having a heating element. A connector of the battery includes a first terminal, a second terminal, and a heater terminal. One or more rechargeable battery cells are electrically coupled to the first and second terminals of the connector. The heating element is in contact with a subset of the battery cells, and includes a resistive heater path that is electrically coupled to the first and heater terminals of the connector and generates heat to warm the battery when a heater voltage is applied to the heater terminal. A waterproof material is wrapped around an exterior of the heating element and battery cells and prevents ambient water from contacting the heater element and battery cells. The waterproof material includes an opening to allow at least the first and second terminals of the connector to be electrically coupled to a logic board.