Abstract: Systems and methods for generating return journey notifications include obtaining a request for navigational directions to a target destination. An outbound journey route from an initial location to the target destination can be determined, wherein the outbound journey route includes an estimated outbound journey time. A return journey route from the target destination to a return destination can be determined, wherein the return journey route includes an estimated return journey time. The outbound journey route and/or return journey route can be determined at least in part from one or more of current traffic conditions or historical traffic conditions. One or more notifications regarding the return journey route can be generated when comparing the estimated outbound journey time to the estimated return journey time results in a determination that one or more predetermined criteria are met.

Abstract: Systems and methods data structures queries to manage loading time of multimedia content are provided. A system receives an input audio signal from a computing device and identifies a request. The system identifies a quantized day value and a quantized time value. The system retrieves, via a lookup in a multi-dimensional matrix data structure with the quantized day value and quantized time value, signals for the quantized day value and the quantized time value. The system generates a query with the signals, and applies the query to a multimedia content data structure to identify a plurality of multimedia content items that match the plurality of signals. The system provides an indication of the plurality of multimedia content items that match the signals for the quantized day value and the quantized time value retrieved from the multi-dimensional matrix data structure.

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 and systems for training and/or using a language selection model for use in determining a particular language of a spoken utterance captured in audio data. Features of the audio data can be processed using the trained language selection model to generate a predicted probability for each of N different languages, and a particular language selected based on the generated probabilities. Speech recognition results for the particular language can be utilized responsive to selecting the particular language of the spoken utterance. Many implementations are directed to training the language selection model utilizing tuple losses in lieu of traditional cross-entropy losses. Training the language selection model utilizing the tuple losses can result in more efficient training and/or can result in a more accurate and/or robust model—thereby mitigating erroneous language selections for spoken utterances.

Abstract: The present disclosure provides an application development platform and associated software development kits (“SDKs”) that provide comprehensive services for generation, deployment, and management of machine-learned models used by computer applications such as, for example, mobile applications executed by a mobile computing device. In particular, the application development platform and SDKs can provide or otherwise leverage a unified, cross-platform application programming interface (“API”) that enables access to all of the different machine learning services needed for full machine learning functionality within the application. In such fashion, developers can have access to a single SDK for all machine learning services.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for context scoring adjustments for candidate answer passages. In one aspect, a method includes scoring candidate answer passages. For each candidate answer passage, the system determines a heading vector that describes a path in the heading hierarchy from the root heading to the respective heading to which the candidate answer passage is subordinate; determines a context score based, at least in part, on the heading vector; and adjusts answer score of the candidate answer passage at least in part by the context score to form an adjusted answer score. The system then selects an answer passage from the candidate answer passages based on the adjusted answer scores.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for facilitating input by a user into a form. In one aspect, a method include actions of obtaining a web resource that includes a form, determining a particular field of the form has been selected, determining an intent that corresponds to the form from a first semantic tag in the web resource, determining a parameter of the intent that corresponds to the particular field of the form from a second semantic tag in the web resource, determining a value to suggest for the particular field based at least on the intent and the parameter of the intent, and providing the value for output as a suggestion of input for the particular field.

Abstract: Group actions may be performed on behalf of multiple users based in part on the suitability of the various user devices of the different users to perform such group actions. Different user devices may also be used to generate different query intent determinations for a query such that the query intent determination made by a particular user device may be used to fulfill the query.

Abstract: Methods and apparatus related to identifying one or more messages sent by a user, identifying two or more contacts that are associated with one or more of the messages, determining a strength of relationship score between identified contacts, and utilizing the strength of relationship scores to provide additional information related to the contacts. A strength of relationship score between a contact and one or more other contacts may be determined based on one or more properties of one or more of the messages. In some implementations, contacts groups may be determined based on the strength of relationship scores. In some implementations, contacts groups may be utilized to disambiguate references to contacts in messages. In some implementations, contacts group may be utilized to provide suggestions to the user of additional contacts of a contacts group that includes the indicated recipient contact of a message.

Abstract: The present disclosure is generally related to a data processing system to selectively invoke applications for execution. A data processing system can receive an input audio signal and can parse the input audio signal to identify a command. The data processing system can identify a first functionality of a first digital assistant application hosted on the data processing system in the vehicle and a second functionality of a second digital assistant application accessible via a client device. The data processing system can determine that one of the first functionality or the second functionality supports the command. The data processing system can select one of the first digital assistant application or the second digital assistant application based on the determination. The data processing system invoke one of the first digital assistant application or the second digital assistant application based on the selection.

Abstract: Network source identification via audio signals is provided. A system receives data packets with an input audio signal from a client device. The system identifies a request. The system selects a digital component provided by a digital component provider device. The system identifies audio chimes stored in memory of the client device. The system matches, based on a policy, an identifier of the digital component provider device to a first audio chime stored in the memory of the client device. The system determines, based on a characteristic of the first audio chime, a configuration to combine the digital component with the first audio chime. The system generates an action data structure with the digital component, an indication of the first audio chime, and the configuration. The system transmits the action data structure to the client device to cause the client device to generate an output audio signal.

Abstract: Provided herein are systems and methods of inserting video content. An application may receive a video content item identifying a plurality of segments. The plurality of segments may have a first segment to play primary video content and a second segment to play supplemental video content. The application may identify the second segment from the plurality of segments. The application may generate, responsive to identifying the second segment, a request for the supplemental video content to play in the second segment of the video content item. The request may include selection parameters. The application may transmit, to at least one server, the request for the supplemental video content to cause the at least one server to select a supplemental video content item using the selection parameters. The application may play the supplemental video content received from the at least one server in the second segment.

Abstract: A processor is configured to maintain, for encoding current values related to the transform coefficients a first line buffer and a second line buffer. The current values are arranged along a current scan-order anti-diagonal line. The first line buffer includes first values of a first scan-order anti-diagonal line. The second line buffer includes second values of a second scan-order anti-diagonal line. The processor is further configured to interleave the first values and the second values in a destination buffer; select, using the destination buffer, a probability distribution for coding a current value of the current values; entropy encode, in a compressed bitstream, the current value using the probability distribution; and replace, for coding values of an immediately subsequent scan-order anti-diagonal line to the current scan-order anti-diagonal line, one of the second line buffer or the first line buffer with the current scan-order anti-diagonal line.

Abstract: A computer-implemented method is described. The method includes a computing system receiving an item of digital content from a user device. The computing system generates one or more labels that indicate attributes of the item of digital content. The computing system also generates one or more conversational replies to the item of digital content based on the one or more labels that indicate attributes of the item of digital content. The method also includes the computing system selecting a conversational reply from among the one or more conversational replies and providing the conversational reply for output to the user device.

Abstract: Transform kernel candidates including a vertical transform type associated with a vertical motion and a horizontal transform type associated with a horizontal motion can be encoded or decoded. During an encoding operation, a residual block of a current block is transformed according to a selected transform kernel candidate to produce a transform block. A probability model for encoding the selected transform kernel candidate is then identified based on neighbor transform blocks of the transform block. The selected transform kernel candidate is then encoded according to the probability model. During a decoding operation, the encoded transform kernel candidate is decoded using the probability model. The encoded transform block is then decoded by inverse transforming dequantized transform coefficients thereof according to the decoded transform kernel candidate.

Abstract: Provided herein are systems and methods of classifying video content. At least one server can identify a video content item identifying a plurality of segments to play primary video content. The at least one server can identify a set of words from a segment of the plurality of segments by using at least one of a transcription corresponding to the segment or speech recognition on audio content corresponding to the segment. The at least one server can determine a classification for the segment based on the set of words from the segment. The at least one server can store, in one or more data structures, an association between the video content item and the classification to categorize the segment of the video content item.