Voice Activity Detection and Silence Suppression in a Packet Network

• US 20100106491A1
• Filed: 12/28/2009
• Published: 04/29/2010
• Est. Priority Date: 12/27/2002
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: James, James H., Rosenbluth, Joshua Hal
• Granted Patent: US 8,112,273 B2
• Time in Patent Office: Days
• US Class Current: 704/215
• 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 readable medium containing instructions for controlling a computing device to provide background sound processing during an ongoing call, the instructions comprising:

receiving an input voice signal and a background noise signal by an access gateway and converting the input noise signal into a packetized voice signal and a packetized noise signal;

transmitting the packetized voice signal and the packetized noise signal from the access gateway to an egress gateway via a network;

receiving the packetized voice signal and the packetized noise signal by the egress gateway and converting the packetized voice signal into an output voice signal;

extracting and storing by the egress gateway noise packets from the received packetized noise signal and converting the packetized noise signal into an output noise signal; and

upon ceasing to receive the input voice signal by the access gateway while the call is still ongoing, instructing the egress gateway to continually output the output noise signal.