Back to results
US 11,145,321 B1Granted
Machine learning classifications of aphasia
AssigneeOmniscient Neurotechnology Pty Limited
InventorsMichael Edward Sughrue, Stephane Philippe Doyen, Peter James Nicholas
Life of this patent
Estimating the term…
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing aphasia assessment. One of the methods includes receiving a recording, generating a text transcript of the recording, and generating speech quantifying and comprehension scores which can be used to determine an aphasia classification. Another method includes performing an aphasia assessment on a brain image to obtain an aphasia classification.
Claims20
A method comprising:
- receiving, by a computer system comprising a processor and memory, a recording of spontaneous speech from a subject, the computer system configured to operate:
- using a machine learning speech quantifying classifier to produce a speech quantifying score based at least in part on the spontaneous speech;
- generating, by the feature generator, comprehension feature values from the spontaneous speech;
- using a machine learning comprehension classifier to produce a comprehension score based at least in part on the comprehension feature values, the machine learning comprehension classifier trained using training comprehension feature values and corresponding training comprehension scores;
- using an aphasia classifier to determine an aphasia classification, wherein the outputs of the machine learning speech quantifying classifier and the machine learning comprehension classifier are used as inputs to the aphasia classifier;
- and
- using, by the computer system, the aphasia classification to process at least one of the spontaneous speech and the subject.
4 more elements
A system comprising:
- one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
- receiving a recording of spontaneous speech from a subject;
- using a machine learning speech quantifying classifier to produce a speech quantifying score based at least in part on the spontaneous speech;
- generating comprehension feature values from the spontaneous speech;
- using a machine learning comprehension classifier to produce a comprehension score based at least in part on the comprehension feature values, the machine learning comprehension classifier trained using training comprehension feature values and corresponding training comprehension scores;
- using an aphasia classifier to determine an aphasia classification, wherein the outputs of the machine learning speech quantifying classifier and the machine learning comprehension classifier are used as inputs to the aphasia classifier;
- and
- using the aphasia classification to process at least one of the spontaneous speech and the subject.
5 more elements
Dependencies are inferred from the claim text.