FIELD: speech analysis. SUBSTANCE: method of recognition of separate words with adaptation to announcer is based on predistortion of speech signal in time region with differentiation with smoothing, subsequent segmentation, coding of segments, determination of level and dispersion of noise of communications channel, computation of energy spectrum, measurement of format frequencies, classification of articulatory events and states, formation and sorting of standards of words, computation of distances between standards and realization of unknown word, making decision on recognition or refusal of recognition with addition to vocabulary of standards in process of adaptation to announcer. EFFECT: increased accuracy and authenticity of recognition. 10 cl
Title | Year | Author | Number |
---|---|---|---|
BIOMETRIC METHOD FOR SUBSCRIBER IDENTIFICATION BASED ON SPEECH SIGNAL | 2020 |
|
RU2742040C1 |
METHOD FOR HYBRID GENERATIVE-DISCRIMINATIVE SEGMENTATION OF SPEAKERS IN AUDIO-FLOW | 2013 |
|
RU2530314C1 |
METHOD OF IDENTIFYING SPEAKER FROM ARBITRARY SPEECH PHONOGRAMS BASED ON FORMANT EQUALISATION | 2009 |
|
RU2419890C1 |
USER VERIFICATION METHOD IN AUTHORISED ACCESS SYSTEMS | 2007 |
|
RU2351023C2 |
METHOD OF IDENTIFICATION OF ANNOUNCER AND DEVICE FOR ITS REALIZATION | 2002 |
|
RU2230375C2 |
METHOD FOR RECOGNIZING SPOKEN WORDS | 2005 |
|
RU2296376C2 |
METHOD AND DEVICE FOR IDENTITY VERIFICATION USING VOICE | 2008 |
|
RU2399102C2 |
METHOD FOR CONTACT-DIFFERENCE ACOUSTIC PERSONAL IDENTIFICATION | 2011 |
|
RU2451346C1 |
SYSTEM AND METHOD OF SPEECH RECOGNITION | 2011 |
|
RU2466468C1 |
METHOD FOR PERSON IDENTIFICATION USING ARBITRARY SPEECH RECORDS | 1996 |
|
RU2107950C1 |
Authors
Dates
1995-11-10—Published
1994-04-20—Filed