FIELD: physics.
SUBSTANCE: for each speech signal of a person recorded from a microphone, a sequence of anatomical parameters characteristic for the said person is determined. The probability that the anatomical parameters belong to the said person, as well as the probability that the anatomical parameters do not belong to the said person is determined. Further, the ratio of these probabilities is calculated and then compared with one. Identity is verified. If the ratio of the probabilities is greater than one, the voice belongs to the said person, and if the ratio is less than one, the voice does not belong to the said person.
EFFECT: high accuracy of assessing identity of a voice in order to verify identity from the voice.
2 cl, 7 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD OF IDENTIFYING SPEAKER FROM ARBITRARY SPEECH PHONOGRAMS BASED ON FORMANT EQUALISATION | 2009 |
|
RU2419890C1 |
| PHONEME-ACOUSTIC METHOD OF TEACHING RESONANT SINGING TECHNIQUES | 2019 |
|
RU2715545C1 |
| METHOD AND DEVICE FOR IDENTITY VERIFICATION USING VOICE | 2008 |
|
RU2399102C2 |
| METHOD FOR CONTACT-DIFFERENCE ACOUSTIC PERSONAL IDENTIFICATION | 2011 |
|
RU2451346C1 |
| USER VERIFICATION METHOD IN AUTHORISED ACCESS SYSTEMS | 2007 |
|
RU2351023C2 |
| TRAINING METHOD OF RESONANT SINGING AND SPEAKING USING RESONANCE METRE | 2006 |
|
RU2352998C2 |
| AUTOMATIC PERSON IDENTIFICATION METHOD | 1998 |
|
RU2161826C2 |
| DEVICE FOR SPEECH SIGNAL PROCESSING | 2018 |
|
RU2701120C1 |
| METHOD FOR HYBRID GENERATIVE-DISCRIMINATIVE SEGMENTATION OF SPEAKERS IN AUDIO-FLOW | 2013 |
|
RU2530314C1 |
| VOICE MODULATION DEVICE AND TECHNIQUE | 2003 |
|
RU2333546C2 |
