Speech recognition system for electronic switches in a non-wireline communications network

• US 5,659,597 A
• Filed: 03/22/1994
• Issued: 08/19/1997
• Est. Priority Date: 04/13/1992
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Voice Control Systems, Inc. (Koninklijke Philips N.V.)
• Inventors: Foster, Peter J., Schalk, Thomas B., Bareis, Bernard F.
• Primary Examiner(s): Coles, Sr., Edward L.
• Assistant Examiner(s): LEE, CHEUKFAN
• Application Number:
  US08/216,009
• Time in Patent Office: 1,246 Days
• Field of Search: 379/59, 379/62, 379/63, 379/88, 379/67, 379/211, 379/212, 379/58, 379/94, 379/91, 379/97, 455/33.1, 455/54.1, 455/54.2, 455/56.1, 455/69
• US Class Current: 455/563
• CPC Class Codes: H04B 7/18567 Arrangements for providing additional services to the basic mobile satellite telephony service
• CPC Class Codes: H04M 11/10 with dictation recording and playback systems
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/405 involving speaker-dependent recognition adaptation to speaker for speech recognition G10L15/07
• CPC Class Codes: H04M 3/42204 Arrangements at the exchange for service or number selection by voice at the terminal H04M1/27
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04W 4/00 Services specially adapted for wireless communication networks; Facilities therefor
• CPC Class Codes: H04W 4/18 Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals
• CPC Class Codes: H04W 88/18 Service support devices; Network management devices

Abstract

An advanced telecommunications system is provided for the recognizing of spoken commands over a cellular telephone, satellite telephone, or personal communications network. In the cellular application, for example, a Speech Recognition System interconnects either internally with or as an external peripheral to a cellular telecommunications switch. The Speech Recognition System includes an administrative subsystem, a call processing subsystem, a speaker-dependent recognition subsystem, a speaker-independent recognition subsystem, and a data storage subsystem. The Speech Recognition System also allows for increased efficiency in the cellular telephone network by integrating with the switch or switches as a shared resource. The administrative subsystem of the Speech Recognition System is used to keep statistical logs of pertinent call information. Pre-recorded instructional messages are stored in the memory of the call processing subsystem for instructing a user on his or her progress in using the system. The speaker-independent recognition subsystem allows the user to interact with the system employing non-user specific functions. User specific functions are controlled with the speaker-dependent recognition subsystem. User specific attributes collected by the recognition subsystems are stored in the data storage subsystem.

Claims

1. A voice recognition system for use in a non-wireline telecommunications switch connected between a telephone network and at least one transmission site that communicates with non-wireline units, comprising:

a voice recognizer having a speaker-independent recognition subsystem and a speaker-dependent recognition subsystem for recognizing characters and commands spoken by a non-wireline telephone unit customer, wherein the speaker-independent recognition subsystem recognizes predetermined control commands and digits and the speaker-dependent recognition subsystem recognizes control commands previously stored by the non-wireline telephone unit customer in an off-line process;

prompting means, responsive to a request for service, for providing a prompt to the non-wireline customer to enter at least one spoken identifier providing identifying information for directing a telephone call; and

processor means, operative under the control of a program stored therein and responsive to receipt by the voice recognizer of the at least one spoken identifier from the non-wireline unit customer, for transferring dialing information associated with the identifying information to the non-wireline telecommunications switch to enable routing of the telephone call.

2. The voice recognition system of claim 1 wherein the spoken identifier comprises at least one digit recognized by the speaker-dependent subsystem.

3. The voice recognition system of claim 1 wherein the spoken identifier comprises a keyword recognized by the speaker-dependent subsystem.

4. The voice recognition system of claim 1 wherein the spoken identifier comprises a code recognized by the speaker-dependent subsystem.

5. A voice recognition system for use in a non-wireline telecommunications switch connected between a telephone network and at least one transmission site that communicates with non-wireline units, comprising:

a voice recognizer having a speaker-independent recognition subsystem and a speaker-dependent recognition subsystem for recognizing characters and commands spoken by a non-wireline telephone unit customer, wherein the speaker-independent recognition subsystem recognizes predetermined control commands and characters and the speaker-dependent recognition subsystem recognizes control commands previously stored by the non-wireline telephone unit customer in an off-line process;

announcing means, responsive to a service request from the non-wireline telephone unit customer, for providing an indication to the non-wireline telephone unit customer indicating that the voice recognizer is prepared to receive identifying information to control a call; and

processor means, operative under the control of a program stored therein and responsive to receipt by the voice recognizer of a spoken command from said telephone unit customer, for controlling the announcing means to request the telephone unit customer to confirm whether identifying information for directing a telephone call entered by the non-wireline telephone unit customer has been properly recognized by the voice recognizer;

the processor means further operative under the control of said program for transferring dialing information to the non-wireline telecommunications switching office if the identifying information has been properly recognized by the voice recognizer.

6. The voice recognition system of claim 5 wherein the spoken command comprises at least one digit recognized by the speaker-dependent subsystem.

7. The voice recognition system of claim 5 wherein the spoken command comprises a keyword recognized by the speaker-dependent subsystem.

8. The voice recognition system of claim 5 wherein the spoken command comprises a code recognized by the speaker-dependent subsystem.

9. A non-wireline telecommunications switching office connected between a telephone network and a group of cell sites that communicate with non-wireline telephone units, comprising:

a non-wireline telephone switching exchange for routing incoming and outgoing calls between the telephone units and land-based customers served by the telephone network;

a voice recognizer having a speaker-independent recognition subsystem and a speaker-dependent recognition subsystem for recognizing characters and commands spoken by a non-wireline telephone unit customer, wherein the speaker-independent recognition subsystem recognizes predetermined control commands and characters and the speaker-dependent recognition subsystem recognizes control commands previously stored by the non-wireline telephone unit customer in an off-line process;

announcing means, responsive to a service request from the non-wireline telephone unit customer, for providing an indication to the non-wireline telephone unit customer indicating that the voice recognizer is prepared to receive identifying information to control a call; and

processor means, operative under the control of a program stored therein and responsive to receipt by the voice recognizer of a spoken command from said telephone unit customer, for controlling the announcing means to request the telephone unit customer to confirm whether identifying information for directing a telephone call entered by the non-wireline telephone unit customer has been properly recognized by the voice recognizer;

the processor means further operative under the control of said program for transferring dialing information to the non-wireline telecommunications switching office if the identifying information has been properly recognized by the voice recognizer.

10. The voice recognition system of claim 9 wherein the spoken command comprises at least one digit recognized by the speaker-dependent subsystem.

11. The voice recognition system of claim 9 wherein the spoken command comprises a keyword recognized by the speaker-dependent subsystem.

12. The voice recognition system of claim 9 wherein the spoken command comprises a code recognized by the speaker-dependent subsystem.

13. A voice recognition system for use in a non-wireline line telecommunications switching office connected between a telephone network and a group of cell sites that communicate with non-wireline units, the non-wireline telecommunications switching office including a non-wireline telephone switching exchange for routing incoming and outgoing calls between the non-wireline units and land-based customers served by the telephone network, comprising:

a voice recognizer having a speaker-independent recognition subsystem and a speaker-dependent recognition subsystem for recognizing characters and commands spoken by a non-wireline telephone unit customer, wherein the speaker-independent recognition subsystem recognizes predetermined control commands and characters and the speaker-dependent recognition subsystem recognizes control commands previously stored by the non-wireline telephone unit customer in an off-line process;

announcing means, responsive to a service request from the non-wireline telephone unit customer, for providing an indication to the non-wireline telephone unit customer indicating that the voice recognizer is prepared to receive identifying information to control a call; and

processor means, operative under the control of a program stored therein and responsive to receipt by the voice recognizer of a spoken command from said telephone unit customer, for controlling the announcing means to request the telephone unit customer to confirm whether identifying information for directing a telephone call entered by the non-wireline telephone unit customer has been properly recognized by the voice recognizer;

the processor means further operative under the control of said program and responsive to confirmation of the identifying information by the non-wireline unit customer for controlling the announcing means to prompt the non-wireline unit customer to answer a question uniquely associated with an authorized user of the non-wireline unit; and

wherein the processor means is further operative under the control of said program and responsive to receipt of a correct answer to the question for transferring dialing information to the non-wireline telecommunications switching office for subsequent action if the identifying information has been properly recognized by the voice recognizer.

14. The voice recognition system of claim 13 wherein the spoken command comprises at least one digit recognized by the speaker-dependent subsystem.

15. The voice recognition system of claim 13 wherein the spoken command comprises a keyword recognized by the speaker-dependent subsystem.

16. The voice recognition system of claim 13 wherein the spoken command comprises a code recognized by the speaker-dependent subsystem.