FIELD: medical science.
SUBSTANCE: method for determining parkinsonian signs by voice with using artificial intelligence provides the stages whereat: voice recording or pre-recorded audio recording of the subject is used, performed through the interface of the client electronic device, recording is transmitted to a server through a web service and processed by a neural network trained using a training sample of at least 1000 subjects. Model for determining voice activity is used and fragments which do not contain the sound of the voice are filtered. Softmax neural network activation function is used to determine the degree of confidence in the response. Neural network response on the presence of parkinsonian symptoms in the subject is generated. Response is transmitted to the client device in the form of a probability of the presence of parkinsonism, classifying it into two classes, including the labels "healthy person" or "signs of parkinsonism".
EFFECT: high accuracy of monitoring and simple procedure.
1 cl, 2 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD FOR SPEECH SYNTHESIS WITH TRANSMISSION OF ACCURATE INTONATION OF THE CLONED SAMPLE | 2020 |
|
RU2754920C1 |
METHOD AND SYSTEM FOR EVALUATING QUALITY OF CUSTOMER SERVICE BASED ON ANALYSIS OF VIDEO AND AUDIO STREAMS USING MACHINE LEARNING TOOLS | 2018 |
|
RU2703969C1 |
METHOD FOR PSYCHOTHERAPEUTIC ELIMINATION OF PHOBIAS, DEVICE AND MACHINE-READABLE MEDIUM FOR IMPLEMENTATION OF METHOD | 2023 |
|
RU2822327C1 |
METHOD FOR DIAGNOSING A PATIENT FOR SIGNS OF RESPIRATORY INFECTION BY MEANS OF CNN WITH AN ATTENTION MECHANISM AND A SYSTEM FOR ITS IMPLEMENTATION | 2021 |
|
RU2758648C1 |
METHOD FOR DIAGNOSING SIGNS OF BRONCHOPULMONARY DISEASES ASSOCIATED WITH COVID-19 VIRUS DISEASE | 2021 |
|
RU2758550C1 |
UNCONTROLLED VOICE RESTORATION USING UNCONDITIONED DIFFUSION MODEL WITHOUT TEACHER | 2023 |
|
RU2823017C1 |
METHOD FOR AUDIOVISUAL RECOGNITION OF PERSONAL PROTECTION EQUIPMENT ON HUMAN FACE | 2022 |
|
RU2791415C1 |
CALL CENTRE AUTOMATION PLATFORM USING SPEECH ANALYTICS | 2021 |
|
RU2787530C1 |
DIAGNOSTIC AND REHABILITATION METHOD OF THE PATIENTS WITH VOICE-SPEECH FUNCTION DISORDERS | 2020 |
|
RU2738660C1 |
TECHNOLOGY FOR ANALYZING ACOUSTIC DATA FOR SIGNS OF COVID-19 DISEASE | 2021 |
|
RU2758649C1 |
Authors
Dates
2025-06-06—Published
2023-11-15—Filed