Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
1998-04-28
2001-04-17
Hudspeth, David (Department: 2641)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S249000, C382S116000, C382S118000
Reexamination Certificate
active
06219639
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Technical Field
The present invention relates to methods and apparatus for performing recognition (identification/verification) of individuals and, more particularly, to methods and apparatus for synchronizing biometric and/or non-biometric indicia attributable to the individuals in order to perform such recognition.
2. Discussion of Related Prior Art
In many instances it is necessary to verify that an individual requesting access to a service or a facility is in fact authorized to access the service or facility. Such services may include, for example, banking services, telephone services, credit card services, while the facilities may be, for example, banks, computer systems, or database systems. In such situations, users typically have to write down, type or key in (e.g., on a keyboard) certain information in order to send an order, make a request, obtain a service, perform a transaction or transmit a message.
Verification or authentication of a customer prior to obtaining access to such services or facilities typically relies essentially on the customer's knowledge of passwords or personal identification numbers (PINS) or by the customer interfacing with a remote operator who verifies the customer's knowledge of information such as name, address, social security number, date of birth, or mother's maiden name. In some special transactions, handwriting recognition or signature verification is also used.
However, such conventional user verification techniques present many drawbacks. First, information typically used to verify a user's identity may be easily obtained. Any perpetrator who is reasonably prepared to commit fraud usually finds it easy to obtain such personal information such as the social security number, mother's maiden name or date of birth of his intended target. Regarding security measures for more complex knowledge-based systems which require passwords, PINS or knowledge of the last transaction/message provided during the previous service, such measures are also not reliable mainly because the user is usually unable to remember this information or because many users write the information down thus making the fraudulent perpetrator's job even easier. For instance, it is known that the many unwitting users actually write their PIN on the back of their ATM or smart card.
The shortcomings inherent with the above discussed security measures have prompted an increasing interest in biometric security technology, i.e., verifying a person's identity by personal biological characteristics. Several approaches are known, such as, for example, the recognition of voice print, facial bone structure, signature, face temperature infrared pattern, hand geometry, writing instrument velocity, writing instrument pressure, fingerprint, and retinal print, to name a few.
Of the known biometric approaches, one such approach is voice print identification (or speaker identification), which characterizes a speaker based on his or her voice. Voice print identification is based on the premise that each person can be uniquely identified by their voice. Speaker recognition (identification/verification) can be performed in text-dependent or textprompted mode (where the text of an utterance is prompted by the speech recognizer and recognition depends on the accuracy of the words uttered as compared to the prompted text), or text-independent mode (where the utterances of the speaker are used to perform recognition by comparing the acoustic characteristics of the speaker with acoustic models of previously enrolled speakers, irrespective of the words uttered). Regardless of the mode employed, speaker recognition usually involves the comparison of the utterance with a claimed speaker model. A measure of the match between the model and utterance is thereafter compared to a similar measure obtained over competing models, for instance, cohort or background models. Cohorts are composed of previously enrolled speakers who possess voice (acoustic) characteristics that are substantially similar, i.e., closest, to the speaker who tries to access the service and/or facility. Cohort models are the acoustic models built from acoustic features respectively associated with the cohort speakers. A background model is an average model built from acoustic features over the global population.
Traditionally, recognition systems employing more than one biometric recognition technique such as, for example, face and voice recognition, typically acquire and analyze each biometric feature (facial feature or voice print) sequentially and independently and merely combine the results (i.e., scores) returned by each separate recognition technique in order to obtain a combined result. However, such traditional systems do not utilize the interaction of the biometrics with respect to one another in making the identification or verification. For instance, conventional systems which independently employ face recognition and speaker recognition merely perform face recognition and speaker recognition in a mutually exclusive manner, but do not attempt to synchronize a person's lip movement with his produced speech in order to verify not only the validity of the speaker by speaker recognition, but that indeed the person interacting with the recognition system is indeed speaking the testing utterances rather than synthesizing them or playing them back from a recorder.
Thus, it would be desirable and highly advantageous to provide recognition (identification/verification) systems and methods for permitting individuals access to a service and/or facility that combine and synchronize biometric and/or non-biometric features with one another in order to provide a significant increase in the degree of accuracy of an identification or verification and thus a decrease in fraudulent and/or errant access to the service and/or facility.
SUMMARY OF THE INVENTION
It is an object of the present invention to provide methods and apparatus for recognizing (identifying/verifying) individuals that combine and synchronize biometric and/or non-biometric features with one another in order to provide a significant increase in the degree of accuracy of the recognition.
It is another object of the present invention to provide methods and apparatus for recognizing individuals that combine and synchronize biometric and/or non-biometric features with one another in order to provide a significant reduction in fraudulent and/or errant access to a service and/or facility.
In one embodiment of the present invention, a method for recognizing an individual based on attributes associated with the individual comprises the steps of: pre-storing at least two distinctive attributes of the individual during at least one enrollment session; contemporaneously extracting the at least two distinctive attributes from the individual during a common recognition session; segmenting the pre-stored attributes and the extracted attributes according to a sequence of segmentation units; indexing the segmented pre-stored and extracted attributes so that the segmented pre-stored and extracted attributes corresponding to an identical segmentation unit in the sequence of segmentation units are associated to an identical index; and respectively comparing the segmented pre-stored and extracted attributes associated to the identical index to each other to recognize the individual.
In another embodiment of the present invention, an apparatus employing synchronized speaker recognition, lip reading and lip recognition for recognizing an individual comprises: a speaker recognition system for performing speaker recognition; a lip reading system for performing lip reading; a lip recognition system for performing lip recognition; a camera and pointing system for generating images of the individual for use by the lip reading and lip recognition systems, the speaker recognition system, the lip reading system, the lip recognition system, and the camera and pointing system contemporaneously extracting biometric attributes correspondi
Bakis Raimo
Kanevsky Dimitri
Maes Stephane Herman
F. Chau & Associates LLP
Hudspeth David
International Business Machines - Corporation
Lerner Martin
LandOfFree
Method and apparatus for recognizing identity of individuals... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for recognizing identity of individuals..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for recognizing identity of individuals... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2535949