Operator services using speech processing

• US 5,014,303 A
• Filed: 12/18/1989
• Issued: 05/07/1991
• Est. Priority Date: 12/18/1989
• Status: Expired due to Term

• Current Assignee: TTI Inventions B LLC (Intellectual Ventures LLC)
• Original Assignee: Bell Communications Research, Inc. (Telefonaktiebolaget LM Ericsson)
• Inventors: Velius, George A.
• Primary Examiner(s): Dwyer, James L.
• Application Number:
  US07/452,567
• Time in Patent Office: 505 Days
• Field of Search: 379/265, 379/266, 379/308, 379/309, 379/223, 379/201, 379/213, 379/214, 379/88, 379/67
• US Class Current: 379/266.01
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 3/4931 Directory assistance systems
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: H04M 3/523 with call distribution or queueing

Abstract

Speech compression technology is utilized to reduce the average working time of an operator on directory assistance calls. In particular, a directory assistance call arriving at an automatic call distributor via a directory assistance trunk is first processed by a speech processing system to compress the initial request for a telephone number. The speech processing system is then connected to an operator position to transmit the processed initial order thereto.

Claims

1. A method for processing a directory assistance call comprising the steps of

receiving a call from a subscriber at an automatic call distributor via an incoming trunk,

utilizing said automatic call distributor to connect said call to a speech processing system,

receiving at said speech processing system an initial request for a telephone listing spoken by said subscriber and processing said initial request to shorten the time it takes for an operator to hear the initial request, and

connecting said speech processing system via said automatic call distributor to a specific operator out of a plurality of operators and playing for said specific operator said initial request as processed by said speech processing system.

2. The method of claim 1 wherein said method further comprises:

after said call is connected to said speech processing system, placing a bid by said speech processing system via said automatic call distributor for an operator out of said plurality of available operators, and queuing said bid until said specific operator is available.

3. The method of claim 1 wherein after said call is connected to said speech processing system a generic greeting is played for said subscriber.

4. The method of claim 1 wherein after said specific operator receives said shortened initial request, a communication path is established between said specific operator and said subscriber.

5. The method of claim 1 wherein said processing step comprises spectrally analyzing the speech signal comprising the initial request, deleting brief periods of silence, determining the rate of change of the speech signal spectrum and eliminating redundant information, and automatically recognizing particular words or phrases in said initial request.

6. The method of claim 1 wherein said processing step comprises compressing said initial request.

7. A method for processing calls comprising the steps of:

receiving each of said calls at a speech processing system before connecting each of said calls to a specific operator out of a plurality of operators,

processing at said speech processing system an initial request of each of said calls to shorten the time required by an operator to hear the initial request, and

transmitting the shortened initial request formed as a result of said processing step for each of said calls to a specific one of said operators.

8. The method of claim 7 wherein said method further comprises

after each call is connected to a specific operator, connecting said specific operator to the subscriber initiating the call.

9. A method for processing service calls to be routed to an available operator out of a plurality of operators to reduce the average operator working time on each of said service calls, said method comprising the steps of:

receiving each of said service calls at a speech processing system before connecting each of said service calls to a specific one of said operators,

compressing at said speech processing system an initial service request forming part of each of said service calls, and

transmitting a compressed initial service request formed as a result of said compressing step for each of said service calls to a specific one of said operators.

10. A device for processing service calls transmitted by a telephone network comprising,

speech processing means including means for shortening speech, and

call distribution means in communication with said speech processing means and including means for receiving said service calls from said telephone network, means for connecting said service calls to said speech processing means so that said shortening means can shorten spoken initial service requests contained in said calls, and means for connecting said speech processing means to a specific operator position out of a plurality of operator positions for each of said calls so that an operator can hear each of said initial service requests as shortened by said shortening means.

11. The device of claim 10 wherein said shortening means comprises means for compressing speech.