Intel Corporation

The Boeing Company

Lukasz M Malinowski

Joachim Hofer

Georg Stemmer

Josef G Bauer

Piotr Rozen

Piotr Majcher

Kamil Grzywinski

Piotr Pawliszcze

Michal Stefanowski

Ewelina Ośko

An aviation component inspection device includes a camera, a display, an input device, and a computer. The camera is configured to capture images of an aviation component under inspection. The computer is configured to receive an image from the camera, evaluate the image with one or more machine-learning aviation component-detection models. Each machine-learning aviation component-detection model is previously trained to output at least one confidence score indicating a confidence that a corresponding aviation component is present in the image. The computer is configured to present, via the display, a list of candidate aviation components based on corresponding confidence scores output by the one or more machine-learning aviation component-detection models, and add data previously-associated with a selected candidate aviation component from the list to a digital inspection report responsive to receiving user verification, via the input device, confirming the selected candidate aviation component is present in the image.

Aviation component inspection using image recognition

A computer-implemented method of speech recognition comprises forming a weighted finite state transducer (WFST) having nodes associated with states and interconnected by arcs, and to identify at least one word or word sequence hypothesis, identifying multiple sub-graphs on the WFST, each sub-graph having the same arrangement of multiple states and at least one arc, and propagating tokens in parallel through the sub-graphs, where each sub-graph is stored as a supertoken each having an array of tokens.

System and method of automatic speech recognition using parallel processing for weighted finite state transducer-based speech decoding

Growing community of inventors

Gdansk, Poland

Lukasz M Malinowski