Movatterモバイル変換


[0]ホーム

URL:


RU96116251A - METHOD FOR IDENTIFICATION OF PERSONALITY BY PHONOGRAMS OF SPECIAL ORAL SPEECH - Google Patents

METHOD FOR IDENTIFICATION OF PERSONALITY BY PHONOGRAMS OF SPECIAL ORAL SPEECH

Info

Publication number
RU96116251A
RU96116251ARU96116251/09ARU96116251ARU96116251ARU 96116251 ARU96116251 ARU 96116251ARU 96116251/09 ARU96116251/09 ARU 96116251/09ARU 96116251 ARU96116251 ARU 96116251ARU 96116251 ARU96116251 ARU 96116251A
Authority
RU
Russia
Prior art keywords
speech
phonograms
oral speech
oral
individuality
Prior art date
Application number
RU96116251/09A
Other languages
Russian (ru)
Other versions
RU2107950C1 (en
Inventor
Н.В. Байчаров
И.П. Карлин
Н.Б. Кураченкова
А.Н. Линьков
Н.Ф. Попов
Ю.И. Савельев
И.Н. Тимофеев
А.В. Фесенко
Original Assignee
Н.В. Байчаров
И.П. Карлин
Н.Б. Кураченкова
А.Н. Линьков
Н.Ф. Попов
Ю.И. Савельев
И.Н. Тимофеев
А.В. Фесенко
Filing date
Publication date
Application filed by Н.В. Байчаров, И.П. Карлин, Н.Б. Кураченкова, А.Н. Линьков, Н.Ф. Попов, Ю.И. Савельев, И.Н. Тимофеев, А.В. ФесенкоfiledCriticalН.В. Байчаров
Priority to RU96116251ApriorityCriticalpatent/RU2107950C1/en
Priority claimed from RU96116251Aexternal-prioritypatent/RU2107950C1/en
Application grantedgrantedCritical
Publication of RU2107950C1publicationCriticalpatent/RU2107950C1/en
Publication of RU96116251ApublicationCriticalpatent/RU96116251A/en

Links

Claims (1)

Translated fromRussian
Способ идентификации личности по фонограммам произвольной устной речи, основанный на спектрально-полосно-временном анализе речевого сигнала, выделения характеристик индивидуальности устной речи и в сравнении этих характеристик с эталонными, отличающийся тем, что в качестве характеристик индивидуальности устной речи используют акустические интегральные признаки, являющиеся оценками параметров статистического распределения компонент текущего спектра и гистограмм распределения периодов и частот основного тона, измеренных на фонограммах речи как с произвольным так и фиксированным контекстом, среди которых при адаптивном переобучении выбирают наиболее информативные признаки для речи данного проверяемого лица и независимые от помех и искажений, присутствующих в сравниваемых фонограммах, а также используют лингвистические признаки, фиксируемые экспертом при слуховом анализе фонограмм с применением автоматизированного банка опорных звуковых эталонов диалектных, акцентных и дефектных особенностей устной речи.A method of identifying a person from phonograms of arbitrary oral speech, based on spectral-band-time analysis of a speech signal, highlighting the characteristics of the individuality of oral speech and comparing these characteristics with the reference ones, characterized in that acoustic characteristics are used as characteristics of the individuality of oral speech, which are estimates parameters of the statistical distribution of the components of the current spectrum and histograms of the distribution of periods and frequencies of the fundamental tone, measured on the phonogram Ammah of speech, both with an arbitrary and fixed context, among which, with adaptive retraining, the most informative features for the speech of the person being tested are selected and independent of the interference and distortion present in the compared phonograms, and they also use linguistic features recorded by the expert during auditory analysis of phonograms using an automated bank of reference sound standards for dialect, accent, and defective features of oral speech.
RU96116251A1996-08-081996-08-08Method for person identification using arbitrary speech recordsRU2107950C1 (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
RU96116251ARU2107950C1 (en)1996-08-081996-08-08Method for person identification using arbitrary speech records

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
RU96116251ARU2107950C1 (en)1996-08-081996-08-08Method for person identification using arbitrary speech records

Publications (2)

Publication NumberPublication Date
RU2107950C1 RU2107950C1 (en)1998-03-27
RU96116251Atrue RU96116251A (en)1998-11-20

Family

ID=20184316

Family Applications (1)

Application NumberTitlePriority DateFiling Date
RU96116251ARU2107950C1 (en)1996-08-081996-08-08Method for person identification using arbitrary speech records

Country Status (1)

CountryLink
RU (1)RU2107950C1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
RU2459281C1 (en)*2011-09-152012-08-20Общество с ограниченной ответственностью "Цифрасофт"Device and method to generate signature of acoustic signal, device to identify acoustic signal

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
RU2230375C2 (en)*2002-09-032004-06-10Общество с ограниченной ответственностью "Центр речевых технологий"Method of identification of announcer and device for its realization
JP2010506206A (en)*2006-10-032010-02-25エヴゲニエヴィッチ ナズドラチェンコ、アンドレイ Method for measuring a person's stress state according to voice and apparatus for carrying out this method
RU2419890C1 (en)*2009-09-242011-05-27Общество с ограниченной ответственностью "Центр речевых технологий"Method of identifying speaker from arbitrary speech phonograms based on formant equalisation
RU2530314C1 (en)*2013-04-232014-10-10Общество с ограниченной ответственностью "ЦРТ-инновации"Method for hybrid generative-discriminative segmentation of speakers in audio-flow

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
SU518791A1 (en)*1973-02-231976-06-25Институт Систем Управления Identification by voice
DE2431458C2 (en)*1974-07-011986-05-28Philips Patentverwaltung Gmbh, 2000 Hamburg Procedure and arrangement for automatic speaker recognition
JPS58129684A (en)*1982-01-291983-08-02Toshiba CorpPattern recognizing device

Cited By (1)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
RU2459281C1 (en)*2011-09-152012-08-20Общество с ограниченной ответственностью "Цифрасофт"Device and method to generate signature of acoustic signal, device to identify acoustic signal

Similar Documents

PublicationPublication DateTitle
ReynoldsHTIMIT and LLHDB: speech corpora for the study of handset transducer effects
KünzelBeware of the ‘telephone effect’: the influence of telephone transmission on the measurement of formant frequencies
CN103903627B (en)The transmission method and device of a kind of voice data
KleinschmidtLocalized spectro-temporal features for automatic speech recognition.
SamburSpeaker recognition using orthogonal linear prediction
Zilovic et al.Speaker identification based on the use of robust cepstral features obtained from pole-zero transfer functions
Karlsson et al.Speaker verification with elicited speaking styles in the VeriVox project
Stubbs et al.Algorithms for separating the speech of interfering talkers: Evaluations with voiced sentences, and normal‐hearing and hearing‐impaired listeners
US6266638B1 (en)Voice quality compensation system for speech synthesis based on unit-selection speech database
US5999900A (en)Reduced redundancy test signal similar to natural speech for supporting data manipulation functions in testing telecommunications equipment
JP2005531811A5 (en)
Sharf et al.Relationship between the speech characteristics and effectiveness of telephone interviewers
RU96116251A (en) METHOD FOR IDENTIFICATION OF PERSONALITY BY PHONOGRAMS OF SPECIAL ORAL SPEECH
US7778833B2 (en)Method and apparatus for using computer generated voice
FujimuraOn the second spectral peak of front vowels: a perceptual study of the role of the second and third formants
US5890104A (en)Method and apparatus for testing telecommunications equipment using a reduced redundancy test signal
JPH08286597A (en) Method and apparatus for determining voice quality
StylianouAssessment and correction of voice quality variabilities in large speech databases for concatenative speech synthesis
RU2107950C1 (en)Method for person identification using arbitrary speech records
Siafarikas et al.Wavelet packet based speaker verification.
US20040054524A1 (en)Speech transformation system and apparatus
Lamel et al.Speaker recognition with the switchboard corpus
SpiegelSpeech masking. I. Simultaneous and nonsimultaneous masking within stop/d/and flap/J/closures
Christiansen et al.Noise reduction in speech using adaptive filtering I: Signal processing algorithms
Soron et al.Some Measurements of the Glottal‐Area Waveform

[8]ページ先頭

©2009-2025 Movatter.jp