Voice packet identification based on celp compression parameters

• US 20060095261A1
• Filed: 10/30/2004
• Published: 05/04/2006
• Est. Priority Date: 10/30/2004
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Shae, Zon-Yin, Saha, Debanjan
• Application Number:
  US10/978,055
• Publication Number:
  US 20060095261A1
• Time in Patent Office: Days
• US Class Current: 704/246
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques

Abstract

Mechanisms, and associated methods, for conducting voice analysis (e.g., speaker ID verification) directly from a compressed domain of a voice signal. Preferably, the feature vector is directly segmented, based on its corresponding physical meaning, from the compressed bit stream.

Claims

1. An apparatus for voice signal analysis, said apparatus comprising:

an arrangement for accepting a voice signal conveyed in compressed form; and

an arrangement for conducting voice analysis directly from the compressed form of the voice signal.

2. The apparatus according to claim 1, wherein the voice signal is conveyed in packets.

3. The apparatus according to claim 2, wherein the voice signal is conveyed in packets via the Internet.

4. The apparatus according to claim 3, wherein the packets are conveyed in a packet stream, and the packet stream is sampled with a constant or variable rate in order to reduce the packet transmission rate prior to sending the packets onward for voice packet analysis.

5. The apparatus according to claim 1, further comprising an arrangement for discerning at least one characteristic in the voice signal associated with speaker identity.

6. The apparatus according to claim 1, wherein:

said accepting arrangement is adapted to accept a feature vector associated with the voice signal;

said arrangement for conducting voice analysis is adapted to segment the feature vector from a bit stream of the compressed form of the voice signal.

7. The apparatus according to claim 6, wherein said arrangement for conducting voice analysis is adapted to segment the feature vector based on a corresponding physical meaning.

8. The apparatus according to claim 1, wherein the compressed form of the voice signal has been compressed via a CELP algorithm.

9. The apparatus according to claim 8, wherein the CELP algorithm comprises a G729 algorithm.

10. A method of voice signal analysis, said method comprising the steps of:

accepting a voice signal conveyed in compressed form; and

conducting voice analysis directly from the compressed form of the voice signal.

11. The method according to claim 10, wherein the voice signal is conveyed in packets.

12. The method according to claim 11, wherein the voice signal is conveyed in packets via the Internet.

13. The method according to claim 12, wherein the packets are conveyed in a packet stream, and the packet stream is sampled with a constant or variable rate in order to reduce the packet transmission rate prior to sending the packets onward for voice packet analysis.

14. The method according to claim 10, further comprising the step of discerning at least one characteristic in the voice signal associated with speaker identity.

15. The method according to claim 10, wherein:

said accepting step comprises accepting a feature vector associated with the voice signal;

said step of conducting voice analysis comprises segmenting the feature vector from a bit stream of the compressed form of the voice signal.

16. The method according to claim 15, wherein said step of conducting voice analysis comprises segmenting the feature vector based on a corresponding physical meaning.

17. The method according to claim 10, wherein the compressed form of the voice signal has been compressed via a CELP algorithm.

18. The apparatus according to claim 17, wherein the CELP algorithm comprises a G729 algorithm.

19. A program storage device readable by a machine, tangibly executable a program of instructions executable by the machine to perform method steps for voice signal analysis, said method comprising the steps of:

accepting a voice signal conveyed in compressed form; and

conducting voice analysis directly from the compressed form of the voice signal.