US 11,869,635 B2
System and method for activation and deactivation of cued health assessment
James D. Harper, Boston, MA (US); and Michael Chen, Norwood, MA (US)
Assigned to Sonde Health, Inc., Boston, MA (US)
Filed by Sonde Health, Inc., Boston, MA (US)
Filed on Apr. 12, 2021, as Appl. No. 17/227,448.
Application 17/227,448 is a continuation of application No. 16/679,350, filed on Nov. 11, 2019, granted, now 10,978,181.
Application 16/679,350 is a continuation of application No. 15/809,312, filed on Nov. 10, 2017, granted, now 10,475,530, issued on Nov. 12, 2019.
Claims priority of provisional application 62/420,340, filed on Nov. 10, 2016.
Prior Publication US 2021/0233623 A1, Jul. 29, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 17/00 (2013.01); G16H 10/20 (2018.01); G10L 17/26 (2013.01); G10L 15/22 (2006.01); G16H 50/30 (2018.01); G10L 25/78 (2013.01); G10L 25/66 (2013.01); A61B 5/00 (2006.01); G16H 50/20 (2018.01); A61B 5/16 (2006.01)
CPC G16H 10/20 (2018.01) [A61B 5/4803 (2013.01); G10L 15/22 (2013.01); G10L 17/00 (2013.01); G10L 17/26 (2013.01); G10L 25/66 (2013.01); G10L 25/78 (2013.01); G16H 50/20 (2018.01); G16H 50/30 (2018.01); A61B 5/16 (2013.01); A61B 5/4806 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for activating a cued health assessment, the system comprising:
a voice sample collector for receiving voice samples from a user;
an audio processing module comprising a voice biomarker extractor, a health state classification unit, and a voice sample scheduler;
the voice biomarker extractor for extracting acoustic features from the received voice samples;
the health state classification unit for classifying the received voice samples based on the acoustic features extracted by the voice biomarker extractor, wherein the classification is one of an emotional or affective state of the user, or a physiological change associated with one or more of a cardiovascular system, nervous system, respiratory system, and endocrine system, along with a probability of the classification; and
the voice sample scheduler for activating a cued health assessment module when the probability is more than a set threshold, and activating a passive health assessment module when the probability is less than the set threshold.
 
11. A method of activating a cued health assessment, the method comprising:
receiving voice samples from a user, by a voice sample collector;
extracting acoustic features from the received voice samples, by a voice biomarker extractor of an audio processing module;
classifying the received voice samples, by a health state classification unit of the audio processing module, based on the acoustic features extracted by the voice biomarker extractor, wherein the classification is one of an emotional or affective state of the user, or a physiological change associated with one or more of a cardiovascular system, nervous system, respiratory system, and endocrine system, along with a probability of the classification; and
activating a cued health assessment module when the probability is more than a set threshold, and activating a passive health assessment module when the probability is less than the set threshold, by a voice sample scheduler of the audio processing module.