Back to results
US 11,380,351 B2Granted
System and method for pulmonary condition monitoring and analysis
AssigneeSamsung Electronics Co., Ltd.
InventorsEbrahim Nematihosseinabadi, Md Mahbubur Rahman, Viswam Nathan, Korosh Vatanparvar, Jilong Kuang, Jun Gao
Life of this patent
Estimating the term…
Abstract
A method for pulmonary condition monitoring includes selecting a phrase from an utterance of a user of an electronic device, wherein the phrase matches an entry of multiple phrases. At least one speech feature that is associated with one or more pulmonary conditions within the phrase is identified. A pulmonary condition is determined based on analysis of the at least one speech feature.
Claims20
A method for pulmonary condition monitoring, comprising:
- receiving initial phrase criteria comprising jitter or shimmer for selecting uttered phrases meeting the initial phrase criteria;
- selecting, a phrase from an utterance of a user of an electronic device during interaction with a voice assistant of the electronic device, the selection being based on using the received initial phrase criteria and the electronic device is a personal electronic device of the user;
- generating a phrase bank for the user and storing the selected phrase from the utterance in the phrase bank;
- training a baseline model using the stored selected phrase from the phrase bank, wherein the selected phrase is a voice assistant command for the personal voice assistant;
- capturing, by the baseline model, correlation and dependencies between one or more speech features and the stored selected phrase for one or more pulmonary conditions;
- spotting the stored selected phrase from the phrase bank in an additional utterance during another interaction with the personal voice assistant;
- identifying at least one speech feature that is associated with the one or more pulmonary conditions within the spotted phrase;
- determining a pulmonary condition for the user based on analysis of the at least one speech feature;
- and
- updating the baseline model based on capturing the correlation and dependencies between the at least one feature and the additional utterance for the determined pulmonary condition.
7 more elements
An electronic device comprising:
- a memory storing instructions;
- and
- at least one processor executing the instructions including a process configured to:
- receive initial phrase criteria comprising jitter or shimmer for selecting uttered phrases meeting the initial phrase criteria;
- select, a phrase from an utterance during interaction with a personal voice assistant of the electronic device, the selection based on using the received initial phrase criteria and the electronic device is a personal electronic device of a user;
- generate a phrase bank for the user and store the selected phrase from the utterance in the phrase bank;
- train a baseline model using the stored selected phrase from the phrase bank, wherein the selected phrase is a voice assistant command for the personal voice assistant;
- capture, by the baseline model, correlation and dependencies between one or more speech features and the stored selected phrase for one or more pulmonary conditions;
- spot the stored selected phrase from the phrase bank in an additional utterance during another interaction with the personal voice assistant;
- identify at least one speech feature that is associated with the one or more pulmonary conditions within the spotted phrase;
- determine a pulmonary condition for the user based on analysis of the at least one speech feature;
- and
- update the baseline model based on capturing the correlation and dependencies between the at least one feature and the additional utterance for the determined pulmonary condition.
10 more elements
A non-transitory processor-readable medium that includes a program that when executed by a processor performing a method comprising:
- receiving initial phrase criteria comprising jitter or shimmer for selecting uttered phrases meeting the initial phrase criteria;
- selecting, a phrase from an utterance of a user of an electronic device during interaction with a personal voice assistant, based on using the received initial phrase criteria, and the electronic device is a personal electronic device of the user;
- generating a phrase bank for the user and storing the selected phrase from the utterance in the phrase bank;
- training a baseline model using the stored selected phrase from the phrase bank, wherein the selected phrase is a voice assistant command of the personal voice assistant;
- capturing, by the baseline model, correlation and dependencies between one or more speech features and the stored selected phrase for one or more pulmonary conditions;
- spotting the stored selected phrase from the phrase bank in an additional utterance during another interaction with the personal voice assistant;
- identifying at least one speech feature that is associated with the one or more pulmonary conditions within the spotted phrase;
- determining a pulmonary condition for the user based on analysis of the at least one speech feature;
- and
- updating the baseline model based on capturing the correlation and dependencies between the at least one feature and the additional utterance for the determined pulmonary condition.
7 more elements
Dependencies are inferred from the claim text.