WO2002065455A1 - Evaluation system and method for binary classification systems utilizing unsupervised database - Google Patents
Evaluation system and method for binary classification systems utilizing unsupervised database Download PDFInfo
- Publication number
- WO2002065455A1 WO2002065455A1 PCT/ZA2002/000019 ZA0200019W WO02065455A1 WO 2002065455 A1 WO2002065455 A1 WO 2002065455A1 ZA 0200019 W ZA0200019 W ZA 0200019W WO 02065455 A1 WO02065455 A1 WO 02065455A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- event
- events
- scores
- data
- data samples
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000011156 evaluation Methods 0.000 title claims description 9
- 238000001514 detection method Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 239000000203 mixture Substances 0.000 description 3
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 208000016339 iris pattern Diseases 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/04—Training, enrolment or model building
Definitions
- THIS invention relates to computerized event classification systems
- the system utilizes a speaker model of the claiming speaker
- the model is pre-generated by
- the decision comprises a "yes” for an acceptance or a "no"
- a false rejection is
- a supervised database comprises speech
- landline environment may not be suitable in a landline environment in
- evaluation system for evaluating performance of a computerized event
- input data sample a decision score to be used in a decision on whether the input data sample relates to either an event of a first kind or an
- figure 1 is a block diagram of a known computerized event
- figure 2 is a very basic block diagram of a known speaker
- figure 3 shows examples of typical Detection Error Trade-off
- figure 4 is a block and flow diagram of the system and method
- figure 5 are distribution curves of decision scores obtained by the
- figure 6 shows DET curves for a typical speaker verification
- figure 1 there is shown a known computerized event classification
- the system 10 generates a decision score 20, which is used by the
- figure 2 a known computerized speaker
- the system is typically used with
- system 30 utilizes an input utterance 32 by a speaker to derive a
- rejections are used as an indication of the performance of the system
- the threshold of the system may be adjusted to
- the objects of the invention is to obtain such a curve for a system 30,
- section 50 which is a mixture of impostor pairs and target pairs.
- the method comprises the steps of utilizing the
- the set of scores therefore comprises an unknown number of scores
- invention comprises a data processor 51 shown in figure 4 for estimating parameters of an overall probabilistic parametric model of
- performance estimation stage 57 is utilized to compute DET curves
- DCF detection cost function
- EER equal error rates
- GMM mixture model
- ( o, ) is the normal distribution with mean ⁇ and standard
- the range begins smaller than the sample
- the impostor component parameters are formed from the previously
- the a priori parameters P imp and P tar may be initialized with guesses.
- Adaptation parameter ⁇ can be set to zero and ⁇ to one.
- the EM algorithm is used to obtain a local maximum of the likelihood
- Q(-) is augmented by adding a Lagrange-multiplier term to
- ⁇ k ( ⁇ t P kl x,)/( ⁇ ,P kl ) (16)
- ⁇ k 2 (( ⁇ t P kl x i 2 )/( ⁇ ,Pk,))- ⁇ k (17)
- f-EJ ⁇ 2 + [AC/B-FJ ⁇ + [D-A 2 /B] 0 (18)
- a (A-yC)/B (19)
- the DET curve can be calculated.
- the error For a threshold t, the error
- the integrals are evaluated using the well known error function.
- Curve 72 was determined according to the method according to the
- Such systems may include, but are not
- Such features may include iris patterns, fingerprints, face
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
ZA2001/1284 | 2001-02-15 | ||
ZA200101284 | 2001-02-15 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2002065455A1 true WO2002065455A1 (en) | 2002-08-22 |
Family
ID=25589069
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/ZA2002/000019 WO2002065455A1 (en) | 2001-02-15 | 2002-02-15 | Evaluation system and method for binary classification systems utilizing unsupervised database |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2002065455A1 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080148106A1 (en) * | 2006-12-18 | 2008-06-19 | Yahoo! Inc. | Evaluating performance of binary classification systems |
CN104616653A (en) * | 2015-01-23 | 2015-05-13 | 北京云知声信息技术有限公司 | Word match awakening method, work match awakening device, voice awakening method and voice awakening device |
EP3738510A1 (en) | 2019-05-17 | 2020-11-18 | Biosense Webster (Israel) Ltd | Controlling appearance of displayed markers for improving catheter and tissue visibility |
CN113610905A (en) * | 2021-08-02 | 2021-11-05 | 北京航空航天大学 | Deep learning remote sensing image registration method based on subimage matching and application |
-
2002
- 2002-02-15 WO PCT/ZA2002/000019 patent/WO2002065455A1/en not_active Application Discontinuation
Non-Patent Citations (4)
Title |
---|
A. MARTIN AND M PRZYBOCKI: "The NIST 1999 Speaker Recognition Evaluation - An Overview", NATIONAL INSTITUTE OF STANDARDS AND TECHNOLOGY, 2000, Gaithersburg, MD, USA, pages 1 - 32, XP002200645 * |
DIALOGUE SPOTLIGHT CONSORTIUM: "Large Scale Evaluation of Automatic Speaker Verification Technology", THE CENTRE FOR COMMUNICATION INTERFACE RESEARCH, May 2000 (2000-05-01), University of Edinburgh, XP002200647 * |
HAKAN MELIN: "databases for speaker recognition: activities in cost250 working group 2", COST250 - SPEAKER RECOGNITION IN TELEPHONY, FINAL REPORT 1999, EUROSPEECH COMMISSION DG-XIII, August 2000 (2000-08-01), Brussels, XP002200646 * |
NIKO BRÜMMER AND JASON PELECANOS: "Unsupervised Evaluation of Speaker Verification Systems", PROCEEDINGS A SPEAKER ODYSSEY 2001, 18 June 2001 (2001-06-18) - 22 June 2001 (2001-06-22), Chania, Creta, pages 243 - 248, XP002200648 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080148106A1 (en) * | 2006-12-18 | 2008-06-19 | Yahoo! Inc. | Evaluating performance of binary classification systems |
US8554622B2 (en) * | 2006-12-18 | 2013-10-08 | Yahoo! Inc. | Evaluating performance of binary classification systems |
US8655724B2 (en) | 2006-12-18 | 2014-02-18 | Yahoo! Inc. | Evaluating performance of click fraud detection systems |
CN104616653A (en) * | 2015-01-23 | 2015-05-13 | 北京云知声信息技术有限公司 | Word match awakening method, work match awakening device, voice awakening method and voice awakening device |
EP3738510A1 (en) | 2019-05-17 | 2020-11-18 | Biosense Webster (Israel) Ltd | Controlling appearance of displayed markers for improving catheter and tissue visibility |
CN113610905A (en) * | 2021-08-02 | 2021-11-05 | 北京航空航天大学 | Deep learning remote sensing image registration method based on subimage matching and application |
CN113610905B (en) * | 2021-08-02 | 2024-05-07 | 北京航空航天大学 | Deep learning remote sensing image registration method based on sub-image matching and application |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109584884B (en) | Voice identity feature extractor, classifier training method and related equipment | |
Reynolds et al. | Speaker verification using adapted Gaussian mixture models | |
US6539352B1 (en) | Subword-based speaker verification with multiple-classifier score fusion weight and threshold adaptation | |
KR100307623B1 (en) | Method and apparatus for discriminative estimation of parameters in MAP speaker adaptation condition and voice recognition method and apparatus including these | |
US20080208581A1 (en) | Model Adaptation System and Method for Speaker Recognition | |
CN111418009A (en) | Personalized speaker verification system and method | |
US20070233484A1 (en) | Method for Automatic Speaker Recognition | |
CN108766464B (en) | Digital audio tampering automatic detection method based on power grid frequency fluctuation super vector | |
Pelecanos et al. | Vector quantization based Gaussian modeling for speaker verification | |
Meignier et al. | Evolutive HMM for multi-speaker tracking system | |
WO2002065455A1 (en) | Evaluation system and method for binary classification systems utilizing unsupervised database | |
Chaudhari et al. | Information fusion and decision cascading for audio-visual speaker recognition based on time-varying stream reliability prediction | |
Mami et al. | Speaker recognition by location in the space of reference speakers | |
Zilca | Text-independent speaker verification using utterance level scoring and covariance modeling | |
WO2002029785A1 (en) | Method, apparatus, and system for speaker verification based on orthogonal gaussian mixture model (gmm) | |
Sanderson et al. | Information fusion for robust speaker verification | |
Sarmah | Comparison studies of speaker modeling techniques in speaker verification system | |
Komlen et al. | Text independent speaker recognition using LBG vector quantization | |
ZA200207210B (en) | Evaluation system and method for binary classification systems utilizing unsupervised database. | |
Garcia-Romero et al. | U-norm likelihood normalization in PIN-based speaker verification systems | |
Koschwitz | The effect of speaking style on the performance of a forensic voice comparison system | |
Memon et al. | Information theoretic expectation maximization based Gaussian mixture modeling for speaker verification | |
Chakraborty et al. | An improved approach to open set text-independent speaker identification (OSTI-SI) | |
Lenarczyk et al. | Speaker recognition system based on GMM multivariate probability distributions built-in a digital watermarking token | |
Adikari et al. | Application of automatic speaker verification techniques for forensic evidence evaluation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NO NZ OM PH PL PT RO RU SD SE SG SI SK SL TJ TM TN TR TT TZ UA UG US UZ VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2002/07210 Country of ref document: ZA Ref document number: 200207210 Country of ref document: ZA |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
REG | Reference to national code |
Ref country code: DE Ref legal event code: 8642 |
|
122 | Ep: pct application non-entry in european phase | ||
NENP | Non-entry into the national phase |
Ref country code: JP |
|
WWW | Wipo information: withdrawn in national office |
Country of ref document: JP |