Google Inc.

Rakesh Narayan Iyer

Vincent Wan

Nicholas Julian Pelly

Joseph M Onorato

Keun Young Park

Zhen Song

Lisha Ruan

A method for predicting parametric vocoder parameter includes receiving a text utterance having one or more words, each word having one or more syllables, and each syllable having one or more phonemes. The method also includes receiving, as input to a vocoder model, prosodic features that represent an intended prosody for the text utterance and a linguistic specification. The prosodic features include a duration, pitch contour, and energy contour for the text utterance, while the linguistic specification includes sentence-level linguistic features, word-level linguistic features for each word, syllable-level linguistic features for each syllable, and phoneme-level linguistic features for each phoneme. The method also includes predicting vocoder parameters based on the prosodic features and the linguistic specification. The method also includes providing the predicted vocoder parameters and the prosodic features to a parametric vocoder configured to generate a synthesized speech representation of the text utterance having the intended prosody.

Predicting parametric vocoder parameters from prosodic features

Systems and methods for extracting information from documents are provided. In one example embodiment, a computer-implemented method includes obtaining one or more units of text from an image of a document. The method includes determining one or more annotated values from the one or more units of text and determining a set of candidate labels for each annotated value. The method determines each set of candidate labels by performing a search for the candidate labels based at least in part on a language associated with the document and a location of each annotated value. The method includes determining a canonical label for each annotated value based at least in part on the associated candidate labels, and mapping at least one annotated value to an action that is presented to a user based at least in part on the canonical label associated with the annotated value.

Systems and methods for extracting information from a physical document

Systems and techniques are provided for per-device authentication. A hardware serial number associated with a hardware component of a computing device may be received. The hardware serial number may be converted to a hardware key check. A hardware key associated with a certificate from the computing device may be received. The hardware key may be compared to the hardware check key to obtain a verification of the certificate. The certificate may be verified when the hardware key check matches the hardware key and the certificate may not be verified when the hardware key check does not match the hardware key. A signature associated with the certificate may be verified. Access to the data processing apparatus by the computing device may be permitted when the certificate is verified and the signature is determined to be authentic.

Per-device authentication

A computing system of a vehicle for controlling a vehicle or systems within a vehicle. The computing system comprises a presence-sensitive panel within the vehicle, an infrared camera configured to capture images in a three-dimensional space within the vehicle, at least one processor; and at least one storage device that stores instructions. When the instructions are executed, they case the at least one processor to: receive, from the presence-sensitive panel, a first indication of input, receive, from the infrared camera, a second indication of input, and determine, based on at least one of the first indication of input or the second indication of input, an operation to be performed.

Detecting user interactions with a computing system of a vehicle

An intermediary device may be utilized to form a communication bridge between a vehicle infotainment system and a remote device. The computing device forming the bridge may send and receive the data sent between the motor vehicle infotainment system and the remote device. The intermediary device may mimic the infotainment system or the remote device and/or an instruction sent by the infotainment system and/or the remote device.

Bridge decoder for a vehicle infotainment system

A user may be provided with a representation of their vehicle on the user's mobile device. The vehicle's location may be determined based on one or more signals received from the mobile device and/or the motor vehicle. The device may generate a notification or otherwise store an indication of the motor vehicle's position. A representation of the motor vehicle's location may be provided to the user on the mobile device.

Growing community of inventors

Sunnyvale, CA, United States of America

Rakesh Narayan Iyer