Abstract: Implementations relate to determining a well-formed phrase to suggest to a user to submit in lieu of a not well-formed phrase. The suggestion is rendered via an interface that is provided to a client device of the user. Those implementations relate to determining that a phrase is not well-formed, identifying alternate phrases that are related to the not well-formed phrase, and scoring the alternate phrases to select one or more of the alternate phrases to render via the interface. Some of those implementations are related to identifying that the phrase is not well-formed based on occurrences of the phrase in documents that are generated by a source with the language of the phrase as the primary language of the creator.

Abstract: As part of a dialog session between a user and an automated assistant, implementations can process, using a streaming ASR model, a stream of audio data that captures a portion of a spoken utterance to generate ASR output, process, using an NLU model, the ASR output to generate NLU output, and cause, based on the NLU output, a stream of fulfillment data to be generated. Further, implementations can further determine, based on processing the stream of audio data, audio-based characteristics associated with the portion of the spoken utterance captured in the stream of audio data. Based on the audio-based characteristics and/the stream of NLU output, implementations can determine whether the user has paused in providing the spoken utterance or has completed providing of the spoken utterance. If the user has paused, implementations can cause natural conversation output to be provided for presentation to the user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying a set of resources in response to crawling multiple webpages that use at least one resource in the set. For each resource in the set, a system determines an age of the resource using a timestamp for the resource. The system determines a pre-fetch measure of the resource based on the age of the resource and usage information that describes use of the resource at a webpage. The system selects a first resource from the set based on the pre-fetch measure and determines whether a respective age of the selected first resource exceeds a threshold age. The system generates an index entry for a pre-fetch index. The index entry includes a command to pre-fetch the first resource based on a determination that the respective age of the first resource exceeds the threshold age.

Abstract: A video conferencing system includes a multi-user interaction slate for the execution of applications having a state that is responsive to inputs from multiple attendees of a video conference. The video conferencing system includes a graphical user interface having video slates provided for video streams and multi-user interaction slates for the execution of code that is responsive to inputs provided at multiple client devices. The video conferencing system can determine a current state of a multi-user interaction slate in response to inputs provided by users of the client devices in association with the multi-user interaction slate. The video conferencing system can provide data for rendering the graphical user interface, including video data associated with the video slates and data indicative of the current state of the multi-user interaction slate.

Abstract: The present disclosure provides an on-device machine learning platform that enables sharing of machine-learned models between applications on a computing device. For example, a first application which has a machine-learned model for a specific task can expose the model to other applications through a system level application programming interface (API) for the other applications to use. Communications using the API can be handled by the on-device machine learning platform. In some implementations, some exchange of resources (e.g., computing resources) can be provided so that the first application is compensated for sharing the machine-learned model (e.g., on a per model invocation basis).

Abstract: A computing system and related techniques for selecting content to be automatically converted to speech and provided as an audio signal are provided. A text-to-speech request associated with a first document can be received that includes data associated with a playback position of a selector associated with a text-to-speech interface overlaid on the first document. First content associated with the first document can be determined based at least in part on the playback position, the first content including content that is displayed in the user interface at the playback position. The first document can be analyzed to identify one or more structural features associated with the first content. Speech data can be generated based on the first content and the one or more structural features.

Abstract: A navigation service determines that a first user intends to navigate to a shared destination from a first location, at a first time, and that a second user intends to navigate to the shared destination from a second location, at a second time within a threshold interval of the first time. The navigation service notifies the first user using an electronic notification that the second user intends to navigate to the shared destination, receives from the first user an electronic request to coordinate navigation to the shared destination with the second user, and in response to receiving the electronic request, provides navigation directions to the shared destination to a device associated with the first user in view of a progress of the second user toward the shared destination.

Abstract: Techniques for using contextual information relating to content presented by a television as part of a search query for an information search are presented. A search management component, at a given moment in time during presentation of television-related content by a communication device in or associated with a television, identifies contextual information associated with a section of the television-related content and generates a content identifier timestamp associated with the contextual information and the section of television-related content. A search component augments a search query using the contextual information to facilitate customization of a subset of search results based on the contextual information. The contextual information in the search query can facilitate disambiguating the search query or promoting a search result over another search result in the subset of search results, based on the contextual information, to facilitate customization of the subset of search results.

Abstract: An email payment system and method to provide users with the ability to initiate and send payments to one more recipients via email messaging. A user interface is provided in an email client that allows a user to insert payment with the email. Payment details are collected through one or more payment modals displayed in the email client. A payment object is inserted into the body of the email and is displayed to both the sender and recipient. The payment details captured in the payment object are communicated to a payment processor. The payment processor uses electronic payment accounts associated with the corresponding sender and recipient email addresses to identify the relevant electronic payment accounts and transfer the payment between said accounts. A status of the payment transaction is tracked and displayed within the payment object of the entails residing in both the sender and recipient email client.

Abstract: The present disclosure is generally related to systems and methods of rendering visual components on applications. At least one action-inventory can indicate to render a user interface component. A data processing system can identify a request from an input audio signal from a client device. The client device can display a first application in a foreground process. The data processing system can select an action-inventory to execute the action corresponding to the request by a second application. The data processing system can generate an action data structure using the action-inventory to provide to the second application. The data processing system can determine that an output of the second application is authorized to be presented with the first application. The data processing system can display, on the client device, a user interface component from the second application with the first application.

Abstract: Training and/or utilizing a single neural network model to generate, at each of a plurality of assistant turns of a dialog session between a user and an automated assistant, a corresponding automated assistant natural language response and/or a corresponding automated assistant action. For example, at a given assistant turn of a dialog session, both a corresponding natural language response and a corresponding action can be generated jointly and based directly on output generated using the single neural network model. The corresponding response and/or corresponding action can be generated based on processing, using the neural network model, dialog history and a plurality of discrete resources. For example, the neural network model can be used to generate a response and/or action on a token-by-token basis.

Abstract: Hot word free adaptation, of function(s) of an automated assistant, responsive to determining, based on gaze measure(s) and/or active speech measure(s), that a user is engaging with the automated assistant. Implementations relate to techniques for mitigating false positive occurrences of and/or false negative occurrences, of hot word free adaptation, through utilization of a permissive parameter set in some situation(s) and a restrictive parameter set in other situation(s). For example, utilizing the restrictive parameter set when it is determined that a user is engaged in conversation with additional user(s). The permissive parameter set includes permissive parameter(s) that are more permissive than counterpart(s) in the restrictive parameter set.

Abstract: Systems and methods for generating augmented reality prerenderings can provide the benefit of an augmented reality rendering without requiring the use of user data. Template images can be used instead of user data to protect the user's privacy while enabling the user to see an object or product rendered onto a preferred template image or a variety of template images.

Abstract: Techniques described herein are directed to arbitrating between multiple potentially-responsive, automated-assistant capable electronic devices to determine which should respond to the user's utterance, and/or which should defer to other electronic device(s). In various implementations, a spoken utterance of a user may be detected at a microphone of a first electronic device, a spoken utterance provided by a user. Sound(s) emitted by additional electronic device(s) may also be detected at the microphone. Each of the sound(s) may encode a timestamp corresponding to detection of the spoken utterance at a respective electronic device. Timestamp(s) may be extracted from the sound(s) and compared to a local timestamp corresponding to detection of the spoken utterance at the first electronic device. Based on the comparison, the first electronic device may either invoke an automated assistant locally or defer to one of the additional electronic devices.

Abstract: Systems and methods for quantum random number generation are provided. In some implementations, a method can include obtaining data indicative of a quantum circuit used by the quantum random number generation system to generate a quantum entropy source for determining a random number. The quantum entropy source can include a plurality of output samples. Each output sample can be obtained by measuring an output of the quantum circuit. The method can include performing one or more simulations of the quantum circuit to obtain a simulated output distribution of the quantum circuit without access to data associated with the random number. The method can include providing data indicative of the simulated output distribution for use in a verification process for the quantum random number generation system. The verification process can determine the use of the quantum computing system in generation of the quantum entropy source.

Abstract: Implementations disclosed herein are directed to unsupervised federated training of global machine learning (“ML”) model layers that, after the federated training, can be combined with additional layer(s), thereby resulting in a combined ML model. Processor(s) can: detect audio data that captures a spoken utterance of a user of a client device; process, using a local ML model, the audio data to generate predicted output(s); generate, using unsupervised learning locally at the client device, a gradient based on the predicted output(s); transmit the gradient to a remote system; update weight(s) of the global ML model layers based on the gradient; subsequent to updating the weight(s), train, using supervised learning remotely at the remote system, a combined ML model that includes the updated global ML model layers and additional layer(s); transmit the combined ML model to the client device; and use the combined ML model to make prediction(s) at the client device.