Application US20200152226

Design of Stimuli for Symptom Detection
[+] Show Details

US20200152226

1. A method comprising: (3) (3)

obtaining, using one or more processors of a device, a speech sample from a user uttering a pre-determined first sentence, the pre-determined first sentence designed to detect or emphasize an existing disease-related symptom in the user;

processing the speech sample through a neural network to predict a first set of one or more disease-related symptoms of the user; and

generating, using the one or more processors and the predicted first set of one or more disease-related symptoms, a second sentence to predict a second set of one or more disease-related symptoms or further confirm or modify the first set of one or more disease-related symptoms.

2. The method of claim 1, wherein the first sentence contains one or more vowels and consonants to enable capturing one or more symptoms. (1) (0)

3. The method of claim 1, wherein the neural network is trained on features extracted from spoken utterances collected from a set of users exhibiting one or more disease-related symptoms as labels. (0)

9. The method of claim 1, wherein the neural network is trained on two groups of data corresponding to the user's uttering: an anchor sentence where no symptoms are detected and the user uttering a same sentence when there is a symptom. (1) (0)

11. The method of claim 9, wherein the second sentence is designed by clustering one or more features from the anchor sentence and first sentence and measuring a distance across the features in each cluster. (3) (0)

4. (canceled) (0)

5. A system comprising: (3) (3)

one or more processors;

memory storing instructions that when executed by the one or more processors, cause the one or more processors to perform operations comprising: obtaining a speech sample from a user uttering a pre-determined first sentence the pre-determined first sentence designed to detect or emphasize one or more existing disease-related symptoms in the user;

processing the speech sample through a neural network to predict a first set of one or more disease-related symptoms of the user; and

generating, using the predicted first set of one or more disease-related symptoms, a second sentence to predict a second set of one or more disease-related symptoms or confirm the first set of one or more disease-related symptoms.

6. The system of claim 5, wherein the first sentence contains one or more vowels and consonants to capture one or more symptoms. (1) (0)

7. The system of claim 5, wherein the neural network is trained on features extracted from spoken utterances collected from a set of users exhibiting one or more disease-related symptoms. (0)

16. The system of claim 5, wherein a second stage classifier is attached to the clustering model to further detect symptoms from the utterance of the second sentence. (1) (0)

18. The system of claim 16, wherein a second sentence is generated based on the predictions from the neural network or predictions using the first sentence to detect further symptoms or further confirm existing symptoms. (2) (0)

19. The system of claim 18, wherein the second sentence is designed by clustering one or more features from the anchor sentence and first sentence and measuring a distance across the features in each cluster. (2) (0)

20. The system of claim 18, wherein the one or more features represent at least one of vowels, consonants, or the transition from a vowel to a consonant. (1) (0)

8. (canceled) (0)

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Application US20200152226

Design of Stimuli for Symptom Detection

Patent Matrix® Search