Speech analysis based answer detection for IP based telephones

• US 6,697,456 B2
• Filed: 12/07/2001
• Issued: 02/24/2004
• Est. Priority Date: 12/07/2001
• Status: Expired due to Term

• Current Assignee: Avaya Incorporated
• Original Assignee: Avaya Technology Corporation Miami Lakes FLA US
• Inventors: Becker, Gary Ray, Chan, Norman Chin-Hung
• Primary Examiner(s): Foster, Roland G.
• Application Number:
  US10/013,048
• Publication Number:
  US 20030108157A1
• Time in Patent Office: 809 Days
• Field of Search: 379/88-1-, 379/88-7-, 379/88-6-, 379/88.22, 379/88.23, 370/351-356, 370/392, 704/231, 704/246, 704/251, 704/275
• US Class Current: 379/88.03
• CPC Class Codes: H04M 1/2535 adapted for voice communication over an Internet Protocol [IP] network Voice over Internet Protocol (VoIP) network equipment and services H04M7/006; implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP] H04L69/16
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 1/82 Line monitoring circuits for call progress or status discrimination for detecting caller identity H04M1/573
• CPC Class Codes: H04M 7/006 Networks other than PSTN/ISDN providing telephone service, e.g. Voice over Internet Protocol (VoIP) , including next generation networks with a packet-switched transport layer H04L65/00 takes precedence; aspects not specific to the type of network H04M3/00; special services in those networks H04M3/42

Abstract

Speaking a predetermined phrase by a user, causes a handset to transmit this audio information to a personal computer. The personal computer is responsive to the predefined phrase to determine that the user of the handset has answered an incoming call.

Claims

1. A method of determining call answer by an IP softphone that is implemented by a personal computer and including an audio transmitter, comprising the steps of:

receiving an incoming call from a telecommunication switching system;

detecting one of a plurality of first predefined speech phrases from the audio transmitter and spoken by a user of the IP softphone; and

accepting the incoming call from the telecommunication switching system in response to the detection of the one of the plurality of first predefined speech phrases;

if the one of the plurality of first predefined speech phrases accepted the incoming call, then buffering the one of the plurality of first predefined speech phrases and a portion of subsequent speech in a buffer as buffered information;

accelerating removal of the buffered information from the buffer such that the removal is faster than speech is received from the audio transmitter; and

transmitting the accelerated buffered information to the telecommunication switching system.

2. The method of claim 1 wherein the step of accelerating comprises eliminating a portion of silence intervals between words.

3. The method of claim 1 wherein the step of accelerating comprises using time domain harmonic scaling.

4. The method of claim 1 wherein the one of the plurality of first predefined speech phrases is user-independent.

5. The method of claim 1 wherein the one of the plurality of first predefined speech phrases is user-dependent.

6. The method of claim 1 further comprises the steps of detecting one of a plurality of predefined audio information segments from the audio transmitter;

and

disconnecting the incoming call from the telecommunication switching system in response to the detection of the one of the plurality of predefined audio information segments.

7. The method of claim 6 wherein the one of the plurality of predefined audio information segments is an user-independent predefined speech phrase.

8. The method of claim 6 wherein the one of the plurality of predefined audio information segments is an user-dependent second predefined speech phrase.

9. The method of claim 6 wherein the one of the plurality predefined audio information segments is a sound of a handset being placed in a stationary position.

10. The method of claim 8 wherein the one of the plurality predefined audio information segments is a sound of a headset being placed in a stationary position.

16. Apparatus for implementing the steps of claim 1.

18. Apparatus for implementing the steps of claim 6.

11. A method of determining call answer by an IP softphone that is implemented by a softphone application and an audio client application executing on a personal computer and including an audio transmitter, comprising the steps of:

receiving an incoming call from a telecommunication switching system;

detecting a first predefined speech phrase from the audio transmitter by the audio client application and spoken by a user of the IP softphone;

accepting the incoming call from the telecommunication switching system by the softphone application in response to the detection of the first predefined speech phrase;

buffering the first predefined speech phrase and a portion of subsequent speech in a buffer as buffered information;

accelerating removal of the buffered information from the buffer such that the removal is faster than speech is received from the audio transmitter;

transmitting the accelerated buffered information to a calling party;

detecting one of a sound of a headset or handset being placed in a stationary position from the audio transmitter by the audio client application; and

disconnecting the incoming call from the telecommunication switching system by the softphone application in response to the detection of the sound.

12. The method of claim 11 wherein the step of accelerating comprises eliminating a portion of silence intervals between words.

13. The method of claim 11 wherein the step of accelerating comprises using time domain harmonic scaling.

14. The method of claim 11 wherein the first predefined speech phrase is user-independent.

15. The method of claim 11 wherein the first predefined speech phrase is user-dependent.

17. Apparatus for implementing the steps of claim 11.