Method for assigning an identification code

• US 7,225,132 B2
• Filed: 03/13/2001
• Issued: 05/29/2007
• Est. Priority Date: 03/14/2000
• Status: Active Grant

• Current Assignee: British Telecommunications PLC (BT Group PLC)
• Original Assignee: British Telecommunications PLC (BT Group PLC)
• Inventors: Marsh, Paul F R, Attwater, David J, Fisher, John S
• Primary Examiner(s): Dorvil; Richemond
• Assistant Examiner(s): Shortledge; Thomas E.
• Application Number:
  US10/203,788
• Publication Number:
  US 20030009321A1
• Time in Patent Office: 2,268 Days
• Field of Search: 704/1, 704/4, 704/243, 704/250, 704/257, 704/273, 704/10, 704/9, 726/28, 713/184
• US Class Current: 704/273
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

An identification code is assigned to a user by making a selection from a closed set of possible tokens. The selection is determined algorithmically by user identity data. The format of the identification code may comprise a sequence of natural language words chosen from closed sets and a separator character having a fixed value or a small range of possible values. The closed sets may be programmed in the recognition grammar of a speech interface to secure services such as banking.

Claims

1. A method of generating a user identification code for a speech recognition system, said user identification code being selected from a finite grammar defining all possible user identification codes, said grammar comprising a first and a second predetermined set of code words, wherein each set comprises a plurality of predefined and limited number of code words, and said sets being in a predetermined order, the method comprising the steps of:

a) receiving identification data corresponding to a user, said identification data comprising input words;

b) selecting a code word for each input word from the predetermined sets of code words, wherein the step of selecting comprises;

for an input word that is equal to one of the plurality of code words in the first set, selecting said code word from the first set, and

for an input word that is not equal to one of the plurality of code words in the first set, selecting from the second set a code word corresponding to the first character of the input word;

c) concatenating said selected code words in the predetermined order of the grammar to form a sequence for use as the user identification code, and if the formed sequence is equal to a previously formed sequence, then further concatenating a sequence number to the formed sequence to form a unique sequence for use as the user identification code; and

d) storing a record of the user identification code and of the identity of the associated user.

2. A method according to claim 1, wherein the first predetermined set of code words comprises personal names, and the identification data comprises the user'"'"'s name.

3. A method according to claim 1, wherein the finite grammar includes a separator word between a first selected code word and a second selected code word.

4. A method according to claim 3, wherein the separator word has a single character only.

5. A method according to claim 1, wherein the finite grammar includes a phrase associated with one of said predetermined sets of code words and in which the phrase distinguishes between homonyms in said one set of predetermined words.

6. A method according to claim 5, in which the phrase is a number.

7. A method according to claim 1, further comprising:

receiving from the user the user identification code;

verifying the user identification code;

determining the user associated with the verified identification code; and

executing a transaction with the user.

8. A method according to claim 7, wherein receiving from the user the user identification code includes receiving a spoken identification code at a speech recognition device pre-programmed with a recognition grammar comprising the sets of code words.

9. A method according to claim 7, wherein the user identification code is received and the transaction executed via a text interface, and the method further comprises receiving another identification code and executing another transaction via a speech interface.