Voice activity detection and silence suppression in a packet network

• US 8,112,273 B2
• Filed: 12/28/2009
• Issued: 02/07/2012
• Est. Priority Date: 12/27/2002
• Status: Expired due to Term

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: James, James H., Rosenbluth, Joshua Hal
• Primary Examiner(s): Chawan, Vijay B
• Application Number:
  US12/647,863
• Publication Number:
  US 20100106491A1
• Time in Patent Office: 771 Days
• Field of Search: 704/226, 704/215, 704/233, 704/210, 704/207, 704/201, 370/260, 370/466, 370/352, 370/356, 455/570, 379/347, 379/400, 379/406.02, 379/388.02, 379/406.03
• US Class Current: 704/233
• CPC Class Codes: G10L 19/012 Comfort noise or silence coding
• CPC Class Codes: G10L 19/167 Audio streaming, i.e. formatting and decoding of an encoded audio signal representation into a data stream for transmission or storage purposes
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10
• CPC Class Codes: H04J 3/17 in which the transmission channel allotted to a first user may be taken away and re-allotted to a second user if the first user becomes inactive, e.g. TASI speech analysis or identification G10L
• CPC Class Codes: H04L 65/1059 End-user terminal functionalities specially adapted for real-time communication
• CPC Class Codes: H04L 65/80 Responding to QoS

Abstract

The present invention is a system and method that improves upon voice activity detection by packetizing actual noise signals, typically background noise. In accordance with the present invention an access network receives an input voice signal (including noise) and converts the input voice signal into a packetized voice signal. The packetized voice signal is transmitted via a network to an egress network. The egress network receives the packetized voice signal, converts the packetized voice signal into an output voice signal, and outputs the output voice signal. The egress network also extracts and stores noise packets from the received packetized voice signal and converts the packetized noise signal into an output noise signal. When the access network ceases to receive the input voice signal while the call is still ongoing, the access network instructs the egress network to continually output the output noise signal.

Claims

1. A computer-implemented method for silence suppression during a call, the method causing a computing device to perform steps comprising:

receiving, via an access gateway, an input voice signal and a background noise signal;

converting, via the access gateway, the input voice signal into a packetized voice signal and the background noise signal into a packetized noise signal; and

receiving the packetized voice signal and the packetized noise signal via an egress gateway, outputting an output voice signal converted from the packetized voice signal and extracting and storing noise packets from the received packetized noise signal via the egress gateway,

wherein when the access gateway ceases to receive the input voice signal while the call is still ongoing, the access gateway instructs the egress gateway to continually output an output noise signal generated from the stored noise packets.

2. The computer-implemented method of claim 1, wherein the access gateway ceases to receive the input voice signal for a predefined hang-over time prior to instructing the egress gateway to continually output the output noise signal.

3. The computer-implemented method of claim 1, wherein the voice signal and noise signal are received over a Voice over Internet Protocol (VoIP) network.

4. The computer-implemented method of claim 1, wherein the voice signal and noise signal are received over a Voice over Frame network.

5. The computer-implemented method of claim 1, wherein the voice signal and noise signal are received over a Voice over ATM network.

6. The computer-implemented method of claim 1, wherein the input voice signal is received from a speaking party and the output voice signal and output noise signal are output to a listening party.

7. A non-transitory computer-readable storage medium storing instructions which, when executed by a computing device, cause the computing device to perform steps comprising:

receiving, via an access gateway, an input voice signal and a background noise signal;

converting, via the access gateway, the input voice signal into a packetized voice signal and the background noise signal into a packetized noise signal; and

receiving the packetized voice signal and the packetized noise signal via an egress gateway, outputting an output voice signal converted from the packetized voice signal and extracting and storing noise packets from the received packetized noise signal via the egress gateway,

wherein when the access gateway ceases to receive the input voice signal while the call is still ongoing, the access gateway instructs the egress gateway to continually output an output noise signal generated from the stored noise packets.

8. The non-transitory computer-readable storage medium of claim 7, wherein the access gateway ceases to receive the input voice signal for a predefined hang-over time prior to instructing the egress gateway to continually output the output noise signal.

9. The non-transitory computer-readable storage medium of claim 7, wherein the voice signal and noise signal are received over a Voice over Internet Protocol (VoIP) network.

10. The non-transitory computer-readable storage medium of claim 7, wherein the voice signal and noise signal are received over a Voice over Frame network.

11. The non-transitory computer-readable storage medium of claim 7, wherein the voice signal and noise signal are received over a Voice over ATM network.

12. 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 and output noise signal are output to a listening party.

13. An access gateway configured to provide noise processing for a call, the access gateway configured to interface with an egress gateway that converts an input voice signal into a packetized voice signal and converts a background noise signal into a packetized noise signal, the access gateway comprising:

a processor;

a first module controlling the processor to receive an input voice signal and a background noise signal; and

a second module controlling the processor to instruct the egress gateway to continually output an output noise signal generated from the stored noise packets when the first module ceases to receive the input voice signal while the call is still ongoing.

14. The access gateway of claim 13, wherein the egress gateway ceases to receive the input voice signal for predetermined hang over time prior to the egress gateway continually outputting the output noise signal.

15. The access gateway of claim 13, wherein the access gateway uses at least one of VoIP technology, Voice over Frame technology and Voice over ATM technology.

16. The access gateway of claim 13, wherein the first module controls the processor to receive the input voice signal from a speaking party and the second module instructs the egress gateway to output the voice signal and output noise signal to a listening party.