Note US Patent 10,152,988: Selecting speech features for building models for detecting medical conditions

From the Background section of the '988 patent:



Early diagnosis of medical conditions, such as Alzheimer's disease or concussions, may allow for improved treatment and improved quality of life for the person with the medical condition. One method that may be used for detecting medical conditions is to process the speech of a person because the sound of a person's voice or the words used by a person may provide useful information for making a medical diagnosis.

To detect a medical condition from a person's speech, features may be extracted from the speech, and the features may be processed with a mathematical model. The type and number of features extracted from the speech may impact the performance of the model, especially where the amount of training data for training the model is limited. Accordingly, appropriate selection of features may improve the performance of the model.




First issued claim:


A system for training a mathematical model for detecting a medical condition, the system comprising at least one computer configured to: obtain a training corpus comprising speech data items, wherein each speech data item is labelled with a diagnosis value; obtain speech recognition results for each speech data item using automatic speech recognition, wherein the speech recognition results for a speech data item comprise a transcription of the speech data item; compute a plurality of acoustic features for each speech data item in the training corpus, wherein the plurality of acoustic features is computed from the speech data item and wherein computation of the plurality of acoustic features does not use the speech recognition results of the speech data item; compute a plurality of language features for each speech data item in the training corpus by processing the speech recognition results; compute a feature selection score for each feature of the plurality of acoustic features and each feature of the plurality of language features, wherein: the feature selection score for a feature indicates a usefulness of the feature for detecting the medical condition, and the feature selection score is computed using, for each speech data item, a value of the feature and the diagnosis value corresponding to the speech data item; select a plurality of features from the plurality of acoustic features and the plurality of language features using the feature selection scores; train the mathematical model for detecting the medical condition using the selected plurality of features for each speech data item of the training corpus; deploy a computer program product or computer service for detecting the medical condition using the mathematical model; present, by the computer program product or computer service, a prompt to a person; receive, by the computer program product or computer service, a speech data item corresponding to speech of a person in response to the prompt; compute a medical diagnosis score by processing the received speech data item using the mathematical model; and display, by the computer program product or computer service, one or more of the medical diagnosis score or a medical diagnosis based on the medical diagnosis score.