Data processing: speech signal processing – linguistics – language – Speech signal processing – Application
Reexamination Certificate
1997-11-20
2001-03-20
Hudspeth, David R. (Department: 2741)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Application
C704S275000, C704S251000, C455S563000
Reexamination Certificate
active
06205428
ABSTRACT:
BACKGROUND INFORMATION
The present invention is directed to a method and apparatus that reduces a set of stored reference identifiers to a candidate subset of reference identifiers, and, in particular, to a method and apparatus that achieves this reduction by first pruning a set of reference index codes associated with the reference identifiers on the basis of an input identifier provided by a user.
Most institutions, such as banks, department stores, and airlines, allow customers to access over the telephone a wide variety of services and information. Before the advent of touch-tone telephones, a customer would obtain these services and information through interacting with a live operator. As touch-tone telephones became more prevalent in homes, these institutions began switching to automated customer-access systems. After dialing a telephone number, a customer using such systems would be asked to enter an account number, or some other identifier. The user would enter the account number through the keys of a touch-tone keypad. As used herein, the term “identifier” refers to a string of characters that may comprise a plurality of letters, numbers, or both; based on this definition, an identifier may comprise either a random aggregation of characters, an actual word, or the name of a place or a person. Furthermore, as used herein, an identifier may comprise, but is not limited to, a string of characters for identifying a particular product, service, location, or account information.
Today, a user can provide such an identifier to an institution through a number of ways besides touch-tone telephony, including by speaking the identifier into the telephone handset. When the user is prompted to speak the identifier, the institution uses a speech recognition system to produce a recognized identifier based on the spoken identifier. Regardless of how the user enters the identifier, however, once a recognized signal representative of the input identifier has been received at the institution, the institution must match the recognized signal with one of a plurality of pre-stored identifiers, which are also referred to as reference identifiers. After a match between the input identifier and a reference identifier is found, the institution performs a transaction based on the matched reference identifier, such as retrieving account information or ordering a specific product. Finding such a match may take some time, however, since institutions often maintain thousands, if not millions, of reference identifiers. Moreover, the more reference identifiers that an institution must search through in order to find a match with an input identifier, the less accurate this search becomes, especially when the reference identifiers are alphanumeric, which tend to be confused with one another. Matching input identifiers with the wrong reference identifiers at least leads to delays and customer dissatisfaction, and perhaps also to erroneous billing or even to divulging sensitive, confidential information. What is therefore needed is a system that maintains a high degree of accuracy in matching input identifiers with reference identifiers, even when the total number of reference identifiers is quite large, by carrying out a procedure that reduces the total number of reference identifiers to a smaller, more manageable candidate subset of reference identifiers. Since the candidate subset of reference identifiers may include substantially fewer reference identifiers than the total set of reference identifiers, a system that uses the present invention to match an input identifier with a reference identifier will do so more quickly and with a higher degree of accuracy.
SUMMARY OF THE INVENTION
The present invention is directed to a method and apparatus that reduces a set of reference identifiers to a candidate subset of reference identifiers on the basis of an input identifier provided by a user. Each of the reference identifiers is associated with one of a plurality of reference index codes. After receiving the input identifier, the present invention provides a recognized identifier based on the input identifier. The present invention also provides a plurality of confusion sets; each confusion set groups together those characters that have a relatively high likelihood of being confused with one another. After providing the recognized identifier, the present invention determines an index code for the recognized identifier on the basis of the recognized identifier and the plurality of confusion sets. This index code may comprise a digital word comprising a plurality of bits divided into segments. Each segment of the index code is associated with one of the confusion sets, and each segment of the index code encodes the number of characters of the associated confusion set that appears in the recognized identifier. The present invention then determines which of the plurality of reference index codes are within a predetermined distance of the index code for the recognized identifier. The candidate set of reference index codes comprises those index codes that are within the predetermined distance to the index code of the recognized identifier. Moreover, the reference identifiers associated with the candidate set of reference index codes constitute the candidate set of reference identifiers. By reducing a set of reference identifiers to a reduced candidate set of reference identifiers in the above-described manner, the present invention reduces the processing time for finding a match to the recognized identifier, and also enhances the accuracy of finding such a match.
REFERENCES:
patent: 3466394 (1969-09-01), French
patent: 3752904 (1973-08-01), Waterbury
patent: 3896266 (1975-07-01), Waterbury
patent: 3988715 (1976-10-01), Mullan et al.
patent: 4718102 (1988-01-01), Crane et al.
patent: 4783804 (1988-11-01), Juang et al.
patent: 4817156 (1989-03-01), Bahl et al.
patent: 4819271 (1989-04-01), Bahl et al.
patent: 4908865 (1990-03-01), Doddington et al.
patent: 5023912 (1991-06-01), Segawa
patent: 5027406 (1991-06-01), Roberts et al.
patent: 5034989 (1991-07-01), Loh
patent: 5050215 (1991-09-01), Nishimura
patent: 5101345 (1992-03-01), MacPhail
patent: 5125022 (1992-06-01), Hunt et al.
patent: 5127043 (1992-06-01), Hunt et al.
patent: 5167016 (1992-11-01), Bagley et al.
patent: 5179718 (1993-01-01), MacPhail
patent: 5216720 (1993-06-01), Naik et al.
patent: 5255310 (1993-10-01), Kim et al.
patent: 5274560 (1993-12-01), LaRue
patent: 5283833 (1994-02-01), Church et al.
patent: 5297194 (1994-03-01), Hunt et al.
patent: 5303299 (1994-04-01), Hunt et al.
patent: 5365574 (1994-11-01), Hunt et al.
patent: 5384833 (1995-01-01), Cameron
patent: 5418717 (1995-05-01), Su et al.
patent: 5452397 (1995-09-01), Ittycheriah et al.
patent: 5454062 (1995-09-01), LaRue
patent: 5455889 (1995-10-01), Bahl et al.
patent: 5465290 (1995-11-01), Hampton et al.
patent: 5497319 (1996-03-01), Chong et al.
patent: 5499288 (1996-03-01), Hunt et al.
patent: 5502774 (1996-03-01), Bellegarda et al.
patent: 5504805 (1996-04-01), Lee
patent: 5509104 (1996-04-01), Lee et al.
patent: 5517558 (1996-05-01), Schalk
patent: 5519786 (1996-05-01), Courtney et al.
patent: 5526465 (1996-06-01), Carey et al.
patent: 5535120 (1996-07-01), Chong et al.
patent: 5566272 (1996-10-01), Brems et al.
patent: 5577164 (1996-11-01), Kaneko et al.
patent: 5613109 (1997-03-01), Yamauchi et al.
patent: 5623578 (1997-04-01), Mikkilineni
patent: 5623609 (1997-04-01), Kaye et al.
patent: 5640490 (1997-06-01), Hansen et al.
patent: 5642519 (1997-06-01), Martin
patent: 5655058 (1997-08-01), Balasubramanian et al.
patent: 5675647 (1997-10-01), Garneau et al.
patent: 5675704 (1997-10-01), Juang et al.
patent: 5675706 (1997-10-01), Lee et al.
patent: 5677989 (1997-10-01), Rabin et al.
patent: 5677990 (1997-10-01), Junqua
patent: 5680509 (1997-10-01), Gopalakrishnan et al.
patent: 5680511 (1997-10-01), Baker et al.
patent: 5687287 (1997-11-01), Gandhi et al.
patent: 5729656 (1998-03-01), Nahamoo et al.
patent: 5745555 (1998-04-01), Mark
patent: 5748840 (1998-05-01), La Rue
patent: 57
Brown Deborah W.
Goldberg Randy G.
Modi Piyush C.
Rosinski Richard R.
AT&T Corp.
Hudspeth David R.
Kenyon & Kenyon
Wieland Susan
LandOfFree
Confusion set-base method and apparatus for pruning a... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Confusion set-base method and apparatus for pruning a..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Confusion set-base method and apparatus for pruning a... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2479150