Caller interface systems and methods

• US 20050203741A1
• Filed: 03/12/2004
• Published: 09/15/2005
• Est. Priority Date: 03/12/2004
• Status: Active Grant

• Current Assignee: Unify Patente GmbH & Co. KG (Atos Se)
• Original Assignee: Siemens Information And Communication Networks, Inc.
• Inventors: Thwing, Gary
• Granted Patent: US 7,526,429 B2
• Time in Patent Office: Days
• US Class Current: 704/254
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

Caller interface systems and methods are described. In one aspect, a sequence of recognized characters beginning with a first recognized character and ending with a last recognized character is received. Successive characters are selected one at a time from the recognized character sequence in order beginning with the first recognized character. For each selected character, a current potential match set of potential character string matches is constructed by: appending characters selected from a set of misrecognized characters including the selected character to each potential character string match in a prior potential match set constructed for a preceding selected character, if any; and deleting from the current potential match set potential character string matches missing from a list of reference character strings. A reference data item corresponding to the potential character string match in a current potential match set containing one a single potential character string match is transmitted for presentation to a caller after non-matching potential character string matches have been deleted.

Claims

1. A machine-implemented caller interface method, comprising:

receiving a sequence of recognized characters beginning with a first recognized character and ending with a last recognized character;

selecting successive characters one at a time from the recognized character sequence in order beginning with the first recognized character;

for each selected character, constructing a current potential match set of potential character string matches by

appending one or more characters selected from a set of misrecognized characters including the selected character to each potential character string match in a prior potential match set constructed for a preceding selected character, if any, and

deleting from the current potential match set potential character string matches missing from a list of reference character strings; and

transmitting for presentation to a caller a reference data item corresponding to the potential character string match in a current potential match set containing one a single potential character string match after non-matching potential character string matches have been deleted.

2. The method of claim 1, wherein the sequence of recognized characters is received from a speech recognition system.

3. The method of claim 2, further comprising transmitting to the speech recognition system a grammar identifying characters to be recognized.

4. The method of claim 1, wherein each misrecognized character set contains at least one character likely to be misrecognized for the corresponding selected character by a speech recognition system.

5. The method of claim 1, wherein deleting comprises comparing potential character string matches and reference character strings of equal character length.

6. The method of claim 1, wherein the misrecognized character sets and the reference character strings are stored in a single document file.

7. The method of claim 6, wherein each list includes a respective table containing reference character strings of equal character length, and different tables contain reference character strings of different respective character length.

8. The method of claim 1, further comprising transmitting for presentation to the caller reference data items corresponding to the potential character string matches in the current potential match set constructed after all recognized characters in the sequence have been selected.

9. The method of claim 1, further comprising transmitting to the caller a message prompting the caller to spell at least a portion of an identifier of a requested reference data item.

10. The method of claim 9, wherein after all recognized characters in the sequence have been selected and multiple potential character string matches remain in the current potential match set, further comprising transmitting to the caller a message prompting the caller to spell an additional portion of the identifier of the requested data item.

11. A machine-readable medium storing machine-readable instructions for causing a machine to:

receive a sequence of recognized characters beginning with a first recognized character and ending with a last recognized character;

select successive characters one at a time from the recognized character sequence in order beginning with the first recognized character;

for each selected character, construct a current potential match set of potential character string matches by

appending one or more characters selected from a set of misrecognized characters including the selected character to each potential character string match in a prior potential match set constructed for a preceding selected character, if any, and

deleting from the current potential match set potential character string matches missing from a list of reference character strings; and

transmit for presentation to a caller a reference data item corresponding to the potential character string match in a current potential match set containing one a single potential character string match after non-matching potential character string matches have been deleted.

12. The medium of claim 11, further comprising machine-readable instructions for causing a machine to transmit to the speech recognition system a grammar identifying characters to be recognized.

13. The medium of claim 11, wherein each misrecognized character set contains at least one character likely to be misrecognized for the corresponding selected character by a speech recognition system.

14. The medium of claim 11, further comprising machine-readable instructions for causing a machine to compare potential character string matches and reference character strings of equal character length.

15. The medium of claim 11, wherein the misrecognized character sets and the reference character strings are stored in a single document file.

16. The medium of claim 15, wherein each list includes a respective table containing reference character strings of equal character length, and different tables contain reference character strings of different respective character length.

17. The medium of claim 11, further comprising machine-readable instructions for causing a machine to transmit for presentation to the caller reference data items corresponding to the potential character string matches in the current potential match set constructed after all recognized characters in the sequence have been selected.

18. The medium of claim 11, further comprising machine-readable instructions for causing a machine to transmit to the caller a message prompting the caller to spell at least a portion of an identifier of a requested reference data item.

19. The medium of claim 18, further comprising machine-readable instructions for causing a machine to transmit to the caller a message prompting the caller to spell an additional portion of the identifier of the requested data item after all recognized characters in the sequence have been selected and multiple potential character string matches remain in the current potential match set.

20. The medium of claim 11, wherein the machine-readable instructions are implemented in a voice-based extensible markup language.

21. A caller interface system, comprising a voice browser programmed to:

receive a sequence of recognized characters beginning with a first recognized character and ending with a last recognized character;

select successive characters one at a time from the recognized character sequence in order beginning with the first recognized character;

for each selected character, construct a current potential match set of potential character string matches by

appending one or more characters selected from a set of misrecognized characters including the selected character to each potential character string match in a prior potential match set constructed for preceding selected character, if any, and

deleting from the current potential match set potential character string matches missing from a list of reference character strings; and

transmit for presentation to a caller a reference data item corresponding to the potential character string match in a current potential match set containing one a single potential character string match after non-matching potential character string matches have been deleted.

22. The system of claim 21, further comprising a speech recognition system operable to transmit the sequence of recognized characters to the voice browser.

23. The system of claim 22, wherein the voice browser is programmed to transmit to the speech recognition system a grammar identifying characters to be recognized.

24. The system of claim 21, wherein each misrecognized character set contains at least one character likely to be misrecognized for the corresponding selected character by a speech recognition system.

25. The system of claim 21, wherein the voice browser is programmed to compare potential character string matches and reference character strings of equal character length.

26. The system of claim 21, wherein the misrecognized character sets and the reference character strings are stored in a single document file loadable by the voice browser.

27. The system of claim 26, wherein each list includes a respective table containing reference character strings of equal character length, and different tables contain reference character strings of different respective character length.

28. The system of claim 21, wherein the voice browser is programmed to transmit for presentation to the caller reference data items corresponding to the potential character string matches in the current potential match set constructed after all recognized characters in the sequence have been selected.

29. The system of claim 21, the voice browser is programmed to transmit to the caller a message prompting the caller to spell at least a portion of an identifier of a requested reference data item.

30. The system of claim 29, the voice browser is programmed to transmit to the caller a message prompting the caller to spell an additional portion of the identifier of the requested data item after all recognized characters in the sequence have been selected and multiple potential character string matches remain in the current potential match set.