Voice telephone dialing

• US 5,165,095 A
• Filed: 09/28/1990
• Issued: 11/17/1992
• Est. Priority Date: 09/28/1990
• Status: Expired due to Term

• Current Assignee: Texas Instruments, Inc.
• Original Assignee: Texas Instruments, Inc.
• Inventors: Borcherding, Mark A.
• Primary Examiner(s): BROWN, THOMAS
• Application Number:
  US07/590,249
• Time in Patent Office: 781 Days
• Field of Search: 379/88, 379/89, 379/189, 379/196, 379/197, 379/198, 379/199, 379/216, 379/355, 379/361, 379/386, 381/42, 381/43
• US Class Current: 379/88.03
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: H04M 1/271 controlled by voice recognition

Abstract

A method for dialing a telephone, using voice recognition to initiate the dialing and to determine the correct telephone number. The dialing is initiated with a spoken dial command that is recognized by using speaker independent templates that are stored locally with respect to the caller'"'"'s telephone. The correct telephone number is recognized by using speaker dependent templates that are downloaded from a central database or by using speaker independent templates stored locally.

Claims

1. A method of using voice recognition computer processing to direct a caller'"'"'s telephone call to a called destination, comprising the steps of:

identifying the caller;

accessing a database containing speaker dependent speech recognition templates;

downloading said speaker dependent templates from a central database to a local station in communication with said caller'"'"'s telephone;

detecting a dial command spoken by said caller;

accessing a database containing speaker independent speech recognition templates;

comparing said dial command to said speaker independent templates;

detecting a destination identifier spoken by said caller;

accessing a database containing speaker dependent speech recognition templates associated with said caller;

comparing said destination identifier to said speaker dependent templates; and

dialing an appropriate number in response to said comparing steps.

2. The method of claim 1, wherein said step of accessing a database containing speaker independent speech recognition templates further comprises downloading said templates to said local station.

3. The method of claim 1, further comprising the steps of comparing said destination identifier to a set of speaker independent templates.

4. The method of claim 1, wherein said step of identifying said caller is performed using identification numbers and speaker independent templates representing said numbers stored at said local station.

5. The method of claim 1, wherein said step of identifying said caller is performed by detecting the caller'"'"'s spoken name and using speaker dependent templates.

6. The method of claim 1, further comprising the step of providing the caller with a set of permissible dial commands.

7. The method of claim 1, wherein said comparing steps are performed using dedicated signal processors of said local station.

8. A voice recognition system for dialing a telephone, comprising:

a number of local database memories that store speaker independent voice recognition templates;

a central database memory that stores sets of speaker dependent templates, each set associated with a caller, wherein each template represents a destination identifier;

a local processing system programmed for identifying a caller, for accessing said central database memory to request a set of speaker dependent templates associated with said identified caller, for detecting a dial command spoken by said caller, for accessing said speaker independent voice recognition templates stored in at least one of said number of local database memories, for recognizing said dial command using said speaker independent templates, for detecting a destination identifier spoken by said identified caller, for recognizing a destination identifier using said speaker dependent templates and for dialing an appropriate number associated with said recognized destination identifier.

9. The system of claim 8, further comprising a communications system for downloading said set of speaker dependent templates to a local database.

10. The system of claim 8, wherein said local processing system comprises a host processing system and a signal processing system.

11. The system of claim 8, wherein said local database memories further store speaker independent templates for recognizing said destination identifier.

12. The system of claim 8, wherein said local processing system is programmed for recognizing said destination identifier by using speaker independent and speaker dependent templates simultaneously.

13. The system of claim 10, wherein said hose processing system is programmed to download said speaker dependent templates while said signal processing system matches said dial command.

14. A method of using voice recognition computer processing to direct a caller'"'"'s telephone call to a called destination, comprising the steps of:

identifying the caller;

accessing a database containing speaker dependent speech recognition templates;

downloading said speaker dependent templates from a central database to a local station in communication with said caller'"'"'s telephone;

detecting a dial command spoken by said caller;

accessing a database containing speaker independent speech recognition templates;

comparing said dial command to said speaker independent templates;

detecting a destination identifier spoken by said caller;

accessing a database containing speaker dependent speech recognition templates associated with said caller;

simultaneously comparing said destination identifier to said speaker dependent templates and to said speaker independent templates; and

dialing an appropriate number in response to said comparing steps.

15. The method of claim 14, wherein said step of accessing a database containing speaker independent speech recognition templates further comprises downloading said templates to said local station.

16. The method of claim 14, wherein said step of identifying said caller is performed using identification numbers and speaker independent templates representing said numbers.

17. The method of claim 14, wherein said step of identifying said caller is performed by detecting the caller'"'"'s spoken name and using speaker dependent templates.

18. The method of claim 14, further comprising the step of providing the caller with a set of permissible dial commands.

19. A method of using voice recognition computer processing to direct a caller'"'"'s telephone call to a called destination, comprising the steps of:

a) identifying the caller;

b) detecting a dial command spoken by said caller;

c) performing the following substeps i) and ii);

i) accessing a database containing speaker dependent speech recognition templates;

ii) downloading said speaker dependent templates from a central database to a local station in communication with said caller'"'"'s telephone;

while performing the following substeps iii) and iv);

iii) accessing a database containing speaker independent speech recognition templates;

iv) comparing said dial command to said speaker independent templates;

d) detecting a destination identifier spoken by said caller;

e) accessing a database containing speaker dependent speech recognition templates associated with said caller;

f) comparing said destination identifier to said speaker dependent templates; and

g) dialing an appropriate number in response to said comparing steps.

20. The method of claim 19, wherein said substep iii) of accessing a database containing speaker independent speech recognition templates further comprises downloading said templates to said local station.

21. The method of claim 19, further comprising the step of providing the caller with a set of permissible dial commands.

22. The method of claim 19, wherein said step f) of comparing said destination identifier to said speaker dependent templates further includes a step of comparing said destination identifier to said speaker independent templates.