Methods and apparatus for efficiently providing a communication system with speech recognition capabilities

• US 6,229,880 B1
• Filed: 05/21/1998
• Issued: 05/08/2001
• Est. Priority Date: 05/21/1998
• Status: Expired due to Term

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Bell Atlantic Network Services, Inc. (Verizon Communications Inc.)
• Inventors: Vysotsky, George J., Reformato, John R.
• Primary Examiner(s): Hoosain, Allan
• Application Number:
  US09/082,553
• Time in Patent Office: 1,083 Days
• Field of Search: 379/67.1, 379/88.01, 379/88.07, 379/88.13, 379/88.16, 379/88.17, 379/90.01, 379/93.09, 379/100.16, 379/88.02, 379/88.03, 379/88.12 , 379/88.15, 379/88.18, 379/88.22, 379/88.25, 379/201, 379/93.11, 379/93.12, 379/207, 379/93.01, 379/229, 379/230, 379/372, 379/373, 379/421, 379/309, 704/260, 704/270, 704/271, 704/275, 704/246, 704/231, 704/250, 707/100, 707/104, 707/205
• US Class Current: 379/88.01
• CPC Class Codes: H04M 1/64 Automatic arrangements for answering calls; Automatic arrangements for recording messages for absent subscribers; Arrangements for recording conversations centralised dictation systems H04M11/10
• CPC Class Codes: H04M 2201/40 using speech recognition
• 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 3/533 Voice mail systems

Abstract

Methods and apparatus for providing speech recognition capability to callers in a cost efficient manner as part of one or more telephone services are described. Multiple speech recognition units with differing capabilities and therefore implementation costs are provided. Calls are assigned to speech recognition circuits throughout a call based on a signal such as a service type identifier indicating the type of service to be provided to the caller. During different phases of a call different speech recognition units may be used. In addition, different amounts of speech recognition processing capability may be allocated to service a call at different points during a call. In this manner efficient use of available speech recognition resources can be achieved.

Claims

1. A method of performing speech recognition in a communication system using a communication line which connects a system user and a device which provides a service to the system user, the method comprising the step of:

monitoring for a signal indicative of a type of service to be provided to a user of a communication line;

selecting a first one of a plurality of speaker independent speech recognition circuits having differing speech recognition capabilities as a function of the signal indicative of the type of service to be provided;

connecting the first selected one of the plurality of speech recognition circuits to the communication line

monitoring the communication line for an additional signal indicative of a type of service to be provided to the user of the communication line;

selecting a second one of the plurality of speech recognition circuits having a different speech recognition capability than the first selected one of the plurality of speech recognition circuits, as a function of the additional signal indicative of the type of service to be provided; and

connecting the second selected one of the plurality of speaker independent speech recognition circuits to the communication line.

2. The method of claim 1, wherein the signal indicative of a type of service to be provided is a service code signal.

3. The method of claim 1, wherein the signal indicative of a type of service to be provided is a spoken phrase.

4. The method of claim 1, wherein the first selected one of the plurality of speaker independent speech recognition circuits is a combined speaker independent and speaker dependent speech recognition circuit.

5. The method of claim 4, wherein the second selected one of the plurality of speaker independent speech recognition circuits is a speaker independent speech recognition circuit.

6. The method of claim 1, wherein the step of connecting the first selected one of the plurality of speaker independent speech recognition circuits to the communication line includes the step of:

coupling the first speaker independent speech recognition circuit to a speech capture circuit coupled to the communication line.

7. The method of claim 6, wherein the step of connecting the second selected one of the plurality of speaker independent speech recognition circuits to the communication line to substitute for the first selected one of the plurality of speaker independent speech recognition circuits includes the steps of:

disconnecting the first selected one of the plurality of speaker independent speech recognition circuits from the speech capture circuit; and

connecting the second selected one of the plurality of speaker independent speech recognition circuits to the speech capture circuit.

8. The method of claim 6, wherein the communication line is a telephone line and the plurality of speaker independent speech recognition circuits and the speech capture circuit are part of a peripheral device coupled to the communications line.

9. The method of claim 8, further comprising the step of generating a DTMF tone in response to speech.

10. A method of providing a speech recognition capability to peripheral devices included in a telephone system having a caller and a plurality of peripheral devices, the method comprising the steps of:

establishing a first connection, the first connection being between a caller and a first peripheral device including a first speech recognition unit;

establishing a second connection, the second connection being between the first peripheral device and a second peripheral device;

operating a first speech recognition unit included in the first peripheral device to perform a speech recognition operation on speech provided by the caller;

operating the first peripheral device to generate a signal in response to a result of said speech recognition operation, said generated signal including a DTMF tone,

muting the connection from the first peripheral device to the caller during at least a portion of the period in which the DTMF tone is generated; and

supplying the generated signal to the second peripheral device.

11. A method of providing a speech recognition capability to peripheral devices included in a telephone system having a caller and a plurality of peripheral devices, the method comprising the steps of:

establishing a first connection through a telephone switch, the first connection being between a caller and a first peripheral device including a first speech recognition unit;

establishing a second connection through said telephone switch, the second connection being between the first peripheral device and a second peripheral device;

operating a first speech recognition unit included in the first peripheral device to perform a speech recognition operation on speech provided by the caller;

operating the first peripheral device to generate a signal in response to a result of said speech recognition operation;

supplying the generated signal to the second peripheral device; and

operating a second speech recognition unit included in the first peripheral device, during the time in which the connection between the first and second peripheral devices is established, to monitor for speech from the caller indicative of a voice dialing operation.

12. The method of claim 11, wherein the second speech recognition unit monitors for a voice dialing command.

13. The method of claim 11, wherein the second speech recognition unit monitors for a name included in a voice dialing directory associated with the subscriber.

14. The method of claim 11,

wherein the second speech recognition unit includes a central processing unit having a faster clock speed and more memory than the first speech recognition unit; and

wherein the second speech recognition operation includes the step of performing more central processing unit operations per second than are performed when performing speech recognition using the first speech recognition unit.

15. A telephone system comprising:

a telephone;

a first peripheral device for providing a service to a user of the telephone, the first peripheral device being a voice mail system;

a communications network for coupling the telephone to the first peripheral device;

a second peripheral device coupled to the communication network, the second peripheral device including;

a speech recognition circuit for performing a speech recognition operation on speech obtained for said caller;

means for generating a signal indicating the content of speech recognized by said speech recognition circuit; and

means for transmitting the generated signal to the first peripheral device.