Abstract: A computer-implemented method for generating results for a client-requested query involves receiving a query produced by a client communication device, generating a result for the query in response to reception of the query, determining one or more predictive follow-up requests before receiving an actual follow-up request from the client device, and initiating retrieval of information associated with the one or more predictive follow-up requests, and transmitting at least part of the result to the client device, and then transmitting to the client device at least part of the information associated with the one or more predictive follow-up requests.

Abstract: This document describes techniques and apparatuses for performing listen-before-talk procedures on bandwidth parts. These techniques include a user equipment (UE) initiating a first listen-before-talk (LBT) procedure on an active bandwidth part used in a radio resource control (RRC) connection between a UE and a base station. During the first LBT procedure, the UE receives a configuration message from the base station instructing the UE to change the active bandwidth part from the first bandwidth part to a second bandwidth part. Responsively, the UE changes the active bandwidth part and initiates a second LBT procedure on the second bandwidth part.

Abstract: This application is directed to presenting a unified user interface on a network-connected television device. The unified user interface displays media content recommendations selected and organized based on knowledge of a user (e.g., search queries, search results, watch history, purchase history, physical activities). The unified user interface also includes a focus area for displaying a series of media content items (e.g., an advertisement) sequentially according to a temporal order for the purposes of promoting a media content item, product, event or service. In some implementations, playback of a media content item presented on the unified user interface relies on a collaborative implementation of a corresponding media player application and a media content casting application, particularly when the play involves a restricted mode. The content casting application is enabled to play the media content item at the restrict mode when the media player application does not operate in the restricted mode.

Abstract: Implementations determine log-in information indicating whether a user of a first application is logged into a target application and/or a website of the target application. In response to the log-in information indicating that the user is logged into the target application but not logged into the website of the target application, a first selectable element can be displayed at a user interface of the first application to receive user input that causes the target application to be opened. In response to the log-in information indicating that the user is not logged into the target application but is logged into the website of the target application, a second selectable element can be displayed at the first application to receive user input that leads to the website of the target application, or the first selectable element can be assigned a deeplink that leads to the website of the target application.

Abstract: This disclosure describes systems and techniques directed to using a supplementary uplink (SUL) to mitigate a desensitization condition. The described systems and techniques include a user equipment having a desensitization manager application that directs the user equipment to determine a presence of a desensitization condition. The desensitization manager application further directs the user equipment to transmit, to a base station, a first message that requests the base station to allocate, to the user equipment, a portion of resources used for a supplementary uplink between the user equipment and the base station. After receiving a second a message from the base station that identifies the allocated portion of the resources, the desensitization manager application directs the user equipment perform uplink transmissions using the allocated portion of the resources.

Abstract: A method includes collecting user activity data for a first online media item. The user activity data can be data for a user consuming the first online media item. The method further includes segmenting a second online media item into a plurality of segments, and identifying one or more of the plurality of segments with user activity data satisfying one or more criteria. The identified segments comprise a set of frames of the plurality of frames of the second online media item. The method further includes selecting a frame from the set of frames from the second online media item. The method further includes sending a recommendation of the selected frame as a thumbnail recommendation for the second online media item to a client device.

Abstract: Systems and methods for identifying related videos based on elements tagged in the videos are presented. In an aspect, a system includes an identification component configured to identify tagged elements in a video, a matching component configured to identify other videos that include one or more of the tagged elements, and a recommendation component configured to recommend the other videos for viewing based on a current or past request to play the video.

Abstract: An autostereoscopic display system includes a transmissive display panel including a backlight having an array of backlight pixels, a selectively-selectively-transmissive display pixel matrix having a first side facing the backlight and an opposing second side, the selectively-transmissive display pixel matrix comprising an array of display pixels, a first lenticular array disposed between the backlight and the first side of the selectively-transmissive display pixel matrix, and a second lenticular array disposed facing the second side of the selectively-transmissive display pixel matrix. The backlight is configured to separately activate different subsets of the backlight pixels such that light emitted from an activated subset of backlight pixels and transmitted through the first lenticular array, the selectively-transmissive display pixel matrix, and the second lenticular array is emitted by the display panel as display light in a corresponding separate direction relative to the display panel.

Abstract: Systems and methods of combining digital video are described. A system can receive digital video comprising frames. The system can analyze the frames to identify a subset of consecutive frames that have a static portion defined by a spatial region with matching pixels across two or more frames. The system can tag the digital video with an indication of the subset and a trigger that causes transmission, at a temporal offset during playback prior to the subset, of a request for content used to overwrite the static portion. The system can receive the request from the client device, the request transmitted by the client device based on the temporal offset during playback prior to the subset. The system can select and transmit a content item responsive to the request to cause the client device to render the content item at the static portion of the subset.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for the selection, provision and display of one or more digital components during display of content. Methods can include identifying a plurality of digital components that can be presented on the client device. A maximum number of digital components that can be presented in a slot of a content and the time duration of the slot is determined. For each digital component a score is generated based on the duration, position requirement and the number of times the digital component is available for provision within the slot is generated. A first set of digital component is selected based on the scores and provided to the client device.

Abstract: A method for identifying malicious software includes receiving and executing a software application, identifying a plurality of uniform resource identifiers the software application interacts with during execution of the software application, and generating a vector representation for the software application using a feed-forward neural network configured to receive the plurality of uniform resource identifiers as feature inputs. The method also includes determining similarity scores for a pool of training applications, each similarity score associated with a corresponding training application and indicating a level of similarity between the vector representation for the software application and a respective vector representation for the corresponding training application.

Abstract: This application is directed to a method for controlling user experience (UX) operations on an electronic device that executes an application. A touchless UX operation associated with the application has an initiation condition including at least detection of a presence and a gesture in a required proximity range with a required confidence level. The electronic device then determines from a first sensor signal the proximity of the presence with respect to the electronic device. In accordance with a determination that the determined proximity is in the required proximity range, the electronic device determines from a second sensor signal a gesture associated with the proximity of the presence and an associated confidence level of the determination of the gesture. In accordance with a determination that the determined gesture and associated confidence level satisfy the initiation condition, the electronic device initializes the touchless UX operation associated with the application.

Abstract: A method for residual adapters for few-shot text-to-speech speaker adaptation includes obtaining a text-to-speech (TTS) model configured to convert text into representations of synthetic speech, the TTS model pre-trained on an initial training data set. The method further includes augmenting the TTS model with a stack of residual adapters. The method includes receiving an adaption training data set including one or more spoken utterances spoken by a target speaker, each spoken utterance in the adaptation training data set paired with corresponding input text associated with a transcription of the spoken utterance. The method also includes adapting, using the adaption training data set, the TTS model augmented with the stack of residual adapters to learn how to synthesize speech in a voice of the target speaker by optimizing the stack of residual adapters while parameters of the TTS model are frozen.

Abstract: Techniques described herein describe aspects of signal adjustments in user equipment-coordination set, UECS, joint transmissions. A base station analyzes a first joint transmission from multiple user equipments, UEs, participating in a UECS, where the multiple UEs include a coordinating UE of the UECS and at least one non-coordinating UE participating in the UECS. The base station determines that the first joint transmission fails to meet a performance metric and directs the multiple UEs participating in the UECS to add signal adjustments to a second joint transmission.

Abstract: A method includes obtaining a multi-utterance training sample that includes audio data characterizing utterances spoken by two or more different speakers and obtaining ground-truth speaker change intervals indicating time intervals in the audio data where speaker changes among the two or more different speakers occur. The method also includes processing the audio data to generate a sequence of predicted speaker change tokens using a sequence transduction model. For each corresponding predicted speaker change token, the method includes labeling the corresponding predicted speaker change token as correct when the predicted speaker change token overlaps with one of the ground-truth speaker change intervals. The method also includes determining a precision metric of the sequence transduction model based on a number of the predicted speaker change tokens labeled as correct and a total number of the predicted speaker change tokens in the sequence of predicted speaker change tokens.

Abstract: A method includes receiving a sequence of acoustic frames as input to a multilingual automated speech recognition (ASR) model configured to recognize speech in a plurality of different supported languages and generating, by an audio encoder of the multilingual ASR, a higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The method also includes generating, by a language identification (LID) predictor of the multilingual ASR, a language prediction representation for a corresponding higher order feature representation. The method also includes generating, by a decoder of the multilingual ASR, a probability distribution over possible speech recognition results based on the corresponding higher order feature representation, a sequence of non-blank symbols, and a corresponding language prediction representation. The decoder includes monolingual output layer having a plurality of output nodes each sharing a plurality of language-specific wordpiece models.

Abstract: A method for proactive notifications in a voice interface device includes: receiving a first user voice request for an action with an future performance time; assigning the first user voice request to a voice assistant service for performance; subsequent to the receiving, receiving a second user voice request and in response to the second user voice request initiating a conversation with the user; and during the conversation: receiving a notification from the voice assistant service of performance of the action; triggering a first audible announcement to the user to indicate a transition from the conversation and interrupting the conversation; triggering a second audible announcement to the user to indicate performance of the action; and triggering a third audible announcement to the user to indicate a transition back to the conversation and rejoining the conversation.

Abstract: A method includes receiving distillation data including a plurality of out-of-domain training utterances. For each particular out-of-domain training utterance of the distillation data, the method includes generating a corresponding augmented out-of-domain training utterance, and generating, using a teacher ASR model trained on training data corresponding to a target domain, a pseudo-label corresponding to the corresponding augmented out-of-domain training utterance. The method also includes distilling a student ASR model from the teacher ASR model by training the student ASR model using the corresponding augmented out-of-domain training utterances paired with the corresponding pseudo-labels generated by the teacher ASR model.

Abstract: The present disclosure describes techniques and apparatuses that are directed to using memory protection data within a computing device. Techniques include allocating regions of a memory for storing application data and protection data. Techniques also include creating a bitmap having bit values corresponding to memory blocks within the allocated regions. The one or more bit values can be indicative of whether application data and/or protection data are present in a memory block. The techniques and apparatuses can enable memory protection, such as memory security (e.g., encryption) and memory safety (e.g., error correction code (ECC) usage), to be efficiently used while permitting discontiguous memory allocations and without substantial operating system modification.

Abstract: The present disclosure relates to a streaming speech-to-speech conversion model, where an encoder runs in real time while a user is speaking, then after the speaking stops, a decoder generates output audio in real time. A streaming-based approach produces an acceptable delay with minimal loss in conversion quality when compared to other non-streaming server-based models. A hybrid model approach for combines look-ahead in the encoder and a non-causal stacker with non-causal self-attention.