Ford Global Technolgoies, LLC

Ford Motor Company Limited

Francois Charette

Lisa Scaria

Praveen Narayanan

Ryan Burke

Gintaras Vincent Puskorius

Scott Andrew Amman

Keng D Hsueh

Vy Tran

Scott Vincent Myers

Brigitte Frances Mora Richardson

John Edward Huber

Hsiao-An Hsieh

Ali Hassani

Punarjay Chakravarty

Alexandru Mihai Gurghian

Nikhil Nagraj Rao

Anthony Dwayne Cooprider

Ranjani Rangarajan

Michael Alan Blommer

Christopher R Fuller

Andrew Dayton Phillips

Alexandro Walsh

Kaushik Balakrishnan

Jose Enrique Solomon

An Ji

Rick S Hooker

Lakshmi Krishnan

Gary Boes

Bill Covitz

Dimitar Petrov Filev

Vidya Nariyambut Murali

Devesh Upadhyay

Harpreetsingh Banvait

Ashley Elizabeth Micks

Yuksel Gur

Mohamed Ahmad

Iman Soltani Bozchalooi

Shant Tokatyan

Ramchandra Ganesh Karandikar

Ronald Louis Quaglia

Allan Miramonti

Mark Edward Porter

Shruthi Venkat

Suhas Venkatappa

Mark Norman Maskill

Sheau-Fang Lei

Vikas Juneja

Steven Lake

Harish Maruvada

Mike Calkins

Alex Przebienda

David Volker

David Zhou

Sandhya Sridhar

Paul J Joseph Nicastri

Ken D Hsueh

A location of a first object can be determined in an image. A line can be drawn on the first image based on the location of the first object. A deep neural network can be trained to determine a relative location between the first object in the image and a second object in the image based on the line. The deep neural network can be optimized by determining a fitness score that divides a number of deep neural network parameters by a performance score. The deep neural network can be output.

Efficient neural networks

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to train a neural network included in a memory augmented neural network based on one or more images and corresponding ground truth in a training dataset by transforming the one or more images to generate a plurality of one-hundred or more variations of the one or more images including variations in the ground truth and process the variations of the one or more images and store feature points corresponding to each variation of the one or more images in memory associated with the memory augmented neural network. The instructions can include further instructions to process an image acquired by a vehicle sensor with the memory augmented neural network, including comparing a feature variance set for the image acquired by the vehicle sensor to the stored processing parameters for each variation of the one or more images, to obtain an output result.

Vehicle neural network enhancement

An end-to-end deep-learning-based system that can solve both ASR and TTS problems jointly using unpaired text and audio samples is disclosed herein. An adversarially-trained approach is used to generate a more robust independent TTS neural network and an ASR neural network that can be deployed individually or simultaneously. The process for training the neural networks includes generating an audio sample from a text sample using the TTS neural network, then feeding the generated audio sample into the ASR neural network to regenerate the text. The difference between the regenerated text and the original text is used as a first loss for training the neural networks. A similar process is used for an audio sample. The difference between the regenerated audio and the original audio is used as a second loss. Text and audio discriminators are similarly used on the output of the neural network to generate additional losses for training.

Joint automatic speech recognition and text to speech conversion using adversarial neural networks

A speech conversion system is described that includes a hierarchical encoder and a decoder. The system may comprise a processor and memory storing instructions executable by the processor. The instructions may comprise to: using a second recurrent neural network (RNN) (GRU1) and a first set of encoder vectors derived from a spectrogram as input to the second RNN, determine a second concatenated sequence; determine a second set of encoder vectors by doubling a stack height and halving a length of the second concatenated sequence; using the second set of encoder vectors, determine a third set of encoder vectors; and decode the third set of encoder vectors using an attention block.

Hierarchical encoder for speech conversion system

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to generate a first color image of a road environment, determine one or more value decompositions of one or more of the red, green, and blue channels of the first color image, obtain one or more modified singular value decompositions by modifying respective ones of the singular value decompositions by a non-linear equation and reconstruct a second color image based on the modified one or more singular value decompositions. The instructions can include further instructions to train a deep neural network based on the second color image and operate a vehicle based on the deep neural network.

Vehicle neural network

Example natural speech data generation systems and methods are described. In one implementation, a natural speech data generator initiates a game between a first player and a second player and determines a scenario associated with the game. A first role is assigned to the first player and a second role is assigned to the second player. The natural speech data generator receives multiple natural speech utterances by the first player and the second player during the game.

Natural speech data generation systems and methods

A computing system can determine a vehicle command based on a received spoken language command and determined confidence levels. The computing system can operate a vehicle based on the vehicle command. The computing system can further determine the spoken language command by processing audio spectrum data corresponding to spoken natural language with an automatic speech recognition (ASR) system.

Vehicle language processing

Systems, methods, and devices for speech transformation and generating synthetic speech using deep generative models are disclosed. A method of the disclosure includes receiving input audio data comprising a plurality of iterations of a speech utterance from a plurality of speakers. The method includes generating an input spectrogram based on the input audio data and transmitting the input spectrogram to a neural network configured to generate an output spectrogram. The method includes receiving the output spectrogram from the neural network and, based on the output spectrogram, generating synthetic audio data comprising the speech utterance.

Neural network generative modeling to transform speech utterances and augment training data

A computing system can be programmed to receive a spoken language command in response to emitting a spoken language cue and process the spoken language command with a generalized adversarial neural network (GAN) to determine a vehicle command. The computing system can be further programmed to operate a vehicle based on the vehicle command.

A computing system can translate a spoken natural language command into an intermediate constructed language command with a first deep neural network and determine a vehicle command and an intermediate constructed language response with a second deep neural network based on receiving vehicle information. The computing system can translate the intermediate constructed language response into a spoken natural language response with a third deep neural network and operate a vehicle based on the vehicle command.

A method for controlling an autonomous vehicle is disclosed. The method may include receiving image data. The image data may be logistically classified by a first neural network as pertaining to one situation of a plurality of situations. Based on this logistic classification, the image data may be assigned to a second neural network that is specifically trained to address the one situation. The second neural network may perform regression on the image data. Thereafter, the vehicle may be control with a command based on the regression.

Multi-tier network for task-oriented deep neural network

A vehicle is disclosed that includes systems for adjusting the transmittance of one or more windows of the vehicle. The vehicle may include a camera outputting images taken of an occupant within the vehicle. The vehicle may also include an artificial neural network running on computer hardware carried on-board the vehicle. The artificial neural network may be trained to classify the occupant of the vehicle using the images captured by the camera as input. The vehicle may further include a controller controlling transmittance of the one or more windows based on classifications made by the artificial neural network. For example, if the artificial neural network classifies the occupant as squinting or shading his or her eyes with a hand, the controller may reduce the transmittance of a windshield, side window, or some combination thereof.

Vehicle-window-transmittance-control apparatus and method

A processor of a vehicle speech recognition system recognizes speech via domain-specific language and acoustic models. The processor further, in response to the acoustic model having a confidence score for recognized speech falling within a predetermined range defined relative to a confidence score for the domain-specific language model, recognizes speech via the acoustic model only.

Acoustic and domain based speech recognition for vehicles

This disclosure generally relates to a system, apparatus, and method for achieving an adaptive vehicle state-based hands free noise reduction feature. A noise reduction tool is provided for adaptively applying a noise reduction strategy on a sound input that uses feedback speech quality measures and machine learning to develop future noise reduction strategies, where the noise reduction strategies include analyzing vehicle operational state information and external information that are predicted to contribute to cabin noise and selecting noise reducing pre-filter options based on the analysis.

Adaptive vehicle state-based hands-free phone noise reduction with learning capability

A vehicle is disclosed that uses data from different types of on-board sensors to determine whether meteorological precipitation is failing near the vehicle. The vehicle may include an on-board camera capturing image data and an on-board accelerometer capturing accelerometer data. The image data may characterize an area in front of or behind the vehicle. The accelerometer data may characterize vibrations of a windshield of the vehicle. An artificial neural network may run on computer hardware carried on-board the vehicle. The artificial neural network may be trained to classify meteorological precipitation in an environment of the vehicle using the image data and the accelerometer data as inputs. The classifications of the artificial neural network may be used to control one or more functions of the vehicle such as windshield-wiper speed, traction-control settings, or the like.

Multi-sensor precipitation-classification apparatus and method

Growing community of inventors

Tracy, CA, United States of America

Francois Charette