FIELD: information technology.
SUBSTANCE: invention relates to systems for determining the personality of a talking voice-activated user device. Method comprises executing a machine learning algorithm (MLA) for determining a first probability parameter, indicating whether the user's speaking user statement is a user from a set of registered users, execution of user usage frequency analysis for generation, for each user from a set of registered users, a second probability parameter, which is frequency-based a priori probability, generation by an electronic device for each user from a set of registered users of a combined probability based on the associated first probability and second probability, selecting a specific user from a set of registered users as a speaker of the user's subject expression based on the combined probability value.
EFFECT: technical result consists in improvement of identification accuracy of a certain speaking user.
19 cl, 3 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHODS AND ELECTRONIC APPARATUSES FOR IDENTIFYING A STATEMENT OF THE USER BY A DIGITAL AUDIO SIGNAL | 2018 |
|
RU2761940C1 |
| METHOD AND SYSTEM FOR CLASSIFYING AN ELECTRONIC DEVICE USER | 2021 |
|
RU2795152C2 |
| METHOD AND SYSTEM FOR SPEECH SYNTHESIS FROM TEXT | 2017 |
|
RU2692051C1 |
| METHOD AND COMPUTER DEVICE FOR DETERMINING INTENTION ASSOCIATED WITH REQUEST TO CREATE INTENT-DEPENDING RESPONSE | 2017 |
|
RU2711104C2 |
| METHODS AND ELECTRONIC DEVICES FOR DETERMINATION OF INTENT ASSOCIATED WITH UTTERED UTTERANCE OF USER | 2018 |
|
RU2711153C2 |
| ELECTRONIC DEVICE AND ITS CONTROL METHOD | 2020 |
|
RU2792288C1 |
| SPEAKER VERIFICATION | 2017 |
|
RU2697736C1 |
| METHOD AND SYSTEM FOR PROCESSING USER SPOKEN SPEECH FRAGMENT | 2019 |
|
RU2757264C2 |
| DEVICE AND METHOD FOR VOICE INTERACTION WITH PRESERVATION OF CONFIDENTIALITY | 2018 |
|
RU2768506C2 |
| DYNAMIC ACOUSTIC MODEL FOR VEHICLE | 2015 |
|
RU2704746C2 |
