Using voiceprint technology in CALEA surveillance

• US 8,553,854 B1
• Filed: 06/27/2006
• Issued: 10/08/2013
• Est. Priority Date: 06/27/2006
• Status: Expired due to Fees

• Current Assignee: Sprint Spectrum LP (Deutsche Telekom AG)
• Original Assignee: Sprint Spectrum LP (Deutsche Telekom AG)
• Inventors: Weaver, Farni B., Acosta, Irwin Joseph Butac, Paterik, Thomas L.
• Primary Examiner(s): Sing, Simon
• Assistant Examiner(s): BEZUAYEHU, SOLOMON G
• Application Number:
  US11/475,285
• Time in Patent Office: 2,660 Days
• Field of Search: 379/88.01, 379/88.02, 379/33.01, 379/34, 379/38, 379/100.01, 379/100.05, 379/133, 370351-356
• US Class Current: 379/88.02
• CPC Class Codes: H04M 3/2281 Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
• 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

Methods and systems are provided for using voiceprint technology in CALEA surveillance. A media-analysis platform receives packets from a bearer element, the packets comprising media data representing a copy of at least part of a real-time media session. The bearer element is configured to initially send to the platform a copy of each of a plurality of media sessions that traverse the bearer element, and to stop sending a copy of a particular session in response to receiving an instruction from the platform. Responsive to receiving the packets, the platform compares the media data to at least one media-data profile, where each profile is associated with a target of surveillance. The platform determines whether the data matches any of the profiles. If the data does not match any of the profiles, the platform sends an instruction to the bearer element to stop sending the copy of the session.

Claims

1. A method comprising:

a media-analysis platform receiving at least one packet from a bearer element, wherein the at least one packet comprises media data, the media data comprising voice data, representing a copy of at least part of a real-time media session, wherein the bearer element is configured to (i) initially send to the media-analysis platform a copy of each of a plurality of real-time media sessions, each such media session comprising voice communication, that traverse the bearer element and (ii) stop sending a copy of a particular such session to the media-analysis platform in response to receiving an instruction from the media-analysis platform;

responsive to receiving the at least one packet, the media-analysis platform comparing the voice data to at least one voice-data profile maintained by the media-analysis platform, wherein each such profile is associated with a target of surveillance;

the media-analysis platform determining whether the voice data matches any of the at least one voice-data profile; and

if the media-analysis platform determines that the voice data does not match any of the at least one voice-data profile, the media-analysis platform responsively sending an instruction to the bearer element to stop sending the copy of the media session to the media-analysis platform.

2. The method of claim 1, wherein the bearer element comprises at least one of a switch, a router, a media gateway, a media server, and a packet data serving node (PDSN).

3. The method of claim 1, wherein the plurality of media sessions that traverse the bearer element comprises at least one of (i) all real-time media sessions that traverse the bearer element, (ii) all real-time media sessions that traverse a second bearer element, (iii) all real-time media sessions that originate in a particular geographic area, and (iv) all real-time media sessions that terminate in a particular geographic area.

4. The method of claim 1, wherein the media session comprises at least one of a Voice over Internet Protocol (VoIP) session, a Real-time Transport Protocol (RTP) session, and a push-to-talk (PTT) session.

5. The method of claim 1, further comprising, if the media-analysis platform determines that the voice data does match at least one voice-data profile, the media-analysis platform responsively carrying out at least one of (i) recording the media session, (ii) alerting a monitoring entity of the match between the media data and the at least one voice-data profile, and (iii) forwarding a copy of the media session to a monitoring entity.

6. The method of claim 5, wherein the monitoring entity is associated with a law-enforcement agency.

7. A media-analysis platform comprising:

a communication interface;

a processor;

data storage comprising (i) at least one media-data profile, the media-data profile comprising a voice-data profile, wherein each profile is associated with a target of surveillance and (ii) program instructions executable by the processor to;

receive at least one packet from a bearer element, wherein the at least one packet comprises media data, the media data comprising voice data, representing a copy of at least part of a real-time media session, the real-time media session comprising voice communication, wherein the bearer element is configured to (i) initially send to the media-analysis platform a copy of each of a plurality of real-time media sessions that traverse the bearer element and (ii) stop sending a copy of a particular session to the media-analysis platform in response to receiving an instruction from the media-analysis platform;

responsive to receiving the at least one packet, compare the voice data to the at least one voice-data profile;

determine whether the voice data matches any of the at least one voice-data profile;

if the voice data does not match any of the at least one voice-data profile, responsively send an instruction to the bearer element to stop sending the copy of the media session to the media-analysis platform.

8. The media-analysis platform of claim 7, wherein the bearer element comprises at least one of a switch, a router, a media gateway, a media server, and a packet data serving node (PDSN).

9. The media-analysis platform of claim 7, wherein the plurality of media sessions that traverse the bearer element comprises at least one of (i) all real-time media sessions that traverse the bearer element, (ii) all real-time media sessions that traverse a second bearer element, (iii) all real-time media sessions that originate in a particular geographic area, and (iv) all real-time media sessions that terminate in a particular geographic area.

10. The media-analysis platform of claim 7, wherein the media session comprises at least one of a Voice over Internet Protocol (VoIP) session, a Real-time Transport Protocol (RTP) session, and a push-to-talk (PTT) session.

11. The media-analysis platform of claim 7, wherein the data storage further comprises program instructions executable by the processor to, if the voice data does match at least one voice-data profile, responsively carry out at least one of (i) recording the media session, (ii) alerting a monitoring entity of the match between the media data and the at least one voice-data profile, and (iii) forwarding a copy of the media session to a monitoring entity.

12. The media-analysis platform of claim 11, wherein the monitoring entity is associated with a law-enforcement agency.

13. A method comprising:

a bearer element initially sending to a media-analysis platform a copy of at least part of each of a plurality of real-time media sessions, each such real-time media session comprising voice communication, that traverse the bearer element, wherein the copy of the at least part of each real-time media session comprises media data associated with the at least part of the respective media session, wherein the media data comprises voice data;

the bearer element receiving from the media-analysis platform an instruction to stop sending a copy of a particular media session to the media-analysis platform, wherein the instruction is associated with the media-analysis platform determining that the voice data of the particular media session does not match any of at least one voice-data profile maintained by the media-analysis platform, wherein each voice-data profile is associated with a target of surveillance; and

responsive to receiving the instruction, the bearer element no longer sending the copy of the particular media session to the media-analysis platform.

14. The method of claim 13, wherein the the media session comprises at least one of a Voice over Internet Protocol (VoIP) session, a Real-time Transport Protocol (RTP) session, and a push-to-talk (PTT) session.

15. The method of claim 13, wherein the bearer element comprises at least one of a switch, a router, a media gateway, a media server, and a packet data serving node (PDSN).

16. The method of claim 13, wherein the plurality of media sessions that traverse the bearer element comprises at least one of (i) all real-time media sessions that traverse the bearer element, (ii) all real-time media sessions that traverse a second bearer element, (iii) all real-time media sessions that originate in a particular geographic area, and (iv) all real-time media sessions that terminate in a particular geographic area.