Google Inc.

Pedro Gonnet Anders

Victor Carbune

Thomas Deselaers

Sandro Feuz

Daniel M Keysers

Filip Pavetic

Philippe Gervais

Techniques are described herein for determining an information gain score for one or more documents of interest to the user and present information from the documents based on the information gain score. An information gain score for a given document is indicative of additional information that is included in the document beyond information contained in documents that were previously viewed by the user. In some implementations, the information gain score may be determined for one or more documents by applying data from the documents across a machine learning model to generate an information gain score. Based on the information gain scores of a set of documents, the documents can be provided to the user in a manner that reflects the likely information gain that can be attained by the user if the user were to view the documents.

Contextual estimation of link information gain

The present disclosure provides systems and methods that reduce vulnerability of software systems (e.g., machine-learned models) to adversarial attacks by increasing variety within the software system. In particular, a software system can include a number of subcomponents that interoperate using predefined interfaces. To increase variety within the software system, multiple, different versions of one or more of the subcomponents of the software system can be generated. In particular, the different versions of the subcomponent(s) can be different from each other in some way, while still remaining functionally equivalent (e.g., able to perform the same functions with comparable accuracy/success). A plurality of different variants of the software system can be constructed by mixing and matching different versions of the subcomponents. A large amount of variety can be exhibited by the variants of the software system deployed at a given time, thereby leading to increased robustness against adversarial attacks.

Systems and methods for increasing robustness of machine-learned models and other software systems against adversarial attacks

Implementing and applying an adaptive and self-training CAPTCHA ('Completely Automated Public Turing test to tell Computers and Humans Apart') assistant that distinguishes between a computer-generated communication (e.g., speech and/or typed) and communication that originates from a human. The CAPTCHA assistant utilizes a generative adversarial network that is self-training and includes a generator to generate synthetic answers and a discriminator to distinguish between human answers and synthetic answers. The trained discriminator is applied to potentially malicious remote entities, which are provided challenge phrases. Answers from the remote entities are provided to the discriminator to predict whether the answer originated from a human or was computer-generated.

Captcha automated assistant

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for collaboration between multiple voice controlled devices are disclosed. In one aspect, a method includes the actions of identifying, by a first computing device, a second computing device that is configured to respond to a particular, predefined hotword; receiving audio data that corresponds to an utterance; receiving a transcription of additional audio data outputted by the second computing device in response to the utterance; based on the transcription of the additional audio data and based on the utterance, generating a transcription that corresponds to a response to the additional audio data; and providing, for output, the transcription that corresponds to the response.

Generating additional synthesized voice output based on prior utterance and synthesized voice output provided in response to the prior utterance

Techniques are described herein for enabling an automated assistant to adjust its behavior depending on a detected age range and/or 'vocabulary level' of a user who is engaging with the automated assistant. In various implementations, data indicative of a user's utterance may be used to estimate one or more of the user's age range and/or vocabulary level. The estimated age range/vocabulary level may be used to influence various aspects of a data processing pipeline employed by an automated assistant. In various implementations, aspects of the data processing pipeline that may be influenced by the user's age range/vocabulary level may include one or more of automated assistant invocation, speech-to-text ('STT') processing, intent matching, intent resolution (or fulfillment), natural language generation, and/or text-to-speech (&#x201c;TTS&#x201d;) processing. In some implementations, one or more tolerance thresholds associated with one or more of these aspects, such as grammatical tolerances, vocabularic tolerances, etc., may be adjusted.

Automated assistants that accommodate multiple age groups and/or vocabulary levels

Collaborative voice controlled devices

Techniques are described herein for enabling an automated assistant to adjust its behavior depending on a detected vocabulary level or other vocal characteristics of an input utterance provided to an automated assistant. The estimated vocabulary level or other vocal characteristics may be used to influence various aspects of a data processing pipeline employed by the automated assistant. In some implementations, one or more tolerance thresholds associated with, for example, grammatical tolerances or vocabulary tolerances, may be adjusted based on the estimated vocabulary level or vocal characteristics of the input utterance.

Systems and method to resolve audio-based requests in a networked environment

The present disclosure provides systems and methods that leverage machine-learned models (e.g., neural networks) to provide enhanced communication assistance. In particular, the systems and methods of the present disclosure can include or otherwise leverage a machine-learned communication assistance model to detect problematic statements included in a communication and/or provide suggested replacement statements to respectively replace the problematic statements. In one particular example, the communication assistance model can include a long short-term memory recurrent neural network that detects an inappropriate tone or unintended meaning within a user-composed communication and provides one or more suggested replacement statements to replace the problematic statements.

Growing community of inventors

Zurich, Switzerland

Pedro Gonnet Anders