System and method for improved use of voice activity detection

• US 8,391,313 B2
• Filed: 12/28/2009
• Issued: 03/05/2013
• Est. Priority Date: 12/27/2002
• Status: Expired due to Fees

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: James, James H, Rosenbluth, Joshua Hal
• Primary Examiner(s): Phillips, Hassan
• Assistant Examiner(s): JONES, PRENELL P
• Application Number:
  US12/647,926
• Publication Number:
  US 20100100375A1
• Time in Patent Office: 1,163 Days
• Field of Search: None
• US Class Current: 370/466
• CPC Class Codes: G10L 19/012 Comfort noise or silence coding
• CPC Class Codes: G10L 21/0272 Voice signal separating
• CPC Class Codes: H04L 65/1026 at the edge
• CPC Class Codes: H04L 65/1036 at the edge
• CPC Class Codes: H04L 65/1101 Session protocols

Abstract

The present invention is a system and method for packetizing actual noise signals, typically background noise, received by an access gateway from a speaking party and transmitting these packetized noise signals via a network to an egress gateway. The egress gateway converts the packetized noise signal into noise signals suitable for output and transmits the output noise signals to a listening party. When the access gateway detects that no voice signal is being received and only a noise signal is being received for a predetermined period of time, the access gateway instructs the egress network to continually transmit output noise signals to the listening party and ceases to transmit packetized noise signals to the egress gateway.

Claims

1. A non-transitory computer-readable storage medium storing instructions which, when executed by a computing device, cause the computing device to perform silence suppression during a telephone call, the instructions comprising:

receiving at an access network and converting an input voice signal into a packetized voice signal;

receiving, at the access network, and converting an input noise signal into a packetized noise signal;

receiving and converting, at an egress network, the packetized voice signal into an output voice signal;

receiving and converting, at the egress network, the packetized noise signal into an output noise signal; and

when the access network continually receives the input noise signal, ceasing to transmit the packetized noise signal by the access network and instructing the egress network to continuously output the output noise signal.

2. The non-transitory computer-readable storage medium of claim 1, wherein ceasing to transmit the packetized noise signal occurs when the access gateway receives the input noise signal for a predefined hang-over time.

3. The non-transitory computer-readable storage medium of claim 1, wherein the input voice signal is received from a speaking party and the output voice signal is output to a listening party.

4. The non-transitory computer-readable storage medium of claim 1, wherein the method uses at least one of Voice over Internet Protocol (VoIP) technology, Voice over Frame technology, and Voice over asynchronous transfer mode technology.

5. The non-transitory computer-readable storage medium of claim 1, wherein the egress network outputs the output noise signal continuously for a duration of the call.

6. The non-transitory computer-readable storage medium of claim 5, wherein the egress network outputs the output noise signal continuously until another input voice signal is received.

7. A non-transitory computer-readable storage medium storing instructions which, when executed by a computing device, cause the computing device to communicate data signals between an access silence suppressor and an egress silence suppressor, the instructions comprising:

instructing an access gateway to receive and convert an input voice signal into a packetized voice signal and receive and convert an input noise signal into a packetized noise signal;

instructing an egress gateway to receive and convert the packetized voice signal into an output voice signal and receive and convert the packetized noise signal into an output noise signal;

instructing the access gateway to cease transmission of the packetized noise signal through the network after the access gateway ceases to receive the input voice signal; and

instructing the egress gateway to output the output noise signal in a loop after the access gateway ceases to receive the input voice signal.

8. The non-transitory computer-readable storage medium of claim 7, the instructions further comprising:

after the access gateway ceases to receive the input voice signal, instructing the access gateway to receive, packetize and transmit the input noise signal for a predefined hang-over time prior to ceasing transmission of the packetized noise signal.

9. The non-transitory computer-readable storage medium of claim 7, wherein the access gateway and egress gateway communicate via at least one of Voice over Internet Protocol, Voice over Frame, and Voice over asynchronous transfer mode.

10. The non-transitory computer-readable storage medium of claim 7, wherein the input voice signal is received from a speaking party and the output voice signal is output to a listening party.

11. The non-transitory computer-readable storage medium of claim 7, wherein the egress gateway continuously outputs the noise signal until a later voice signal is received.

12. A computer-implemented method of silence management via an access silence suppressor and an egress silence suppressor, the method comprising:

converting, via an access network, a received input voice signal into a packetized voice signal;

converting, via the access network, a received input noise signal into a packetized noise signal;

converting, via the egress network, the received packetized voice signal into an output voice signal;

converting, via the egress network, a received packetized noise signal into an output noise signal; and

ceasing to transmit the packetized noise signal when the access network continually receives the input noise signal and instructing the egress network to repeatedly output the output noise signal.

13. The computer-implemented method of claim 12, wherein the access network receives the input noise signal for a predefined hang-over time prior to ceasing transmission of the packetized noise signal.

14. The computer-implemented method of claim 12, wherein the access network and egress network communicate via at least one of Voice over Internet Protocol, Voice over Frame, and Voice over asynchronous transfer mode.

15. The computer-implemented method of claim 12, wherein the input voice signal is received from a speaking party and the output voice signal is output to a listening party.