CSR: Speaker Recognition from Compressed VoIP Packet Stream

CELP compressed algorithms (e.g., G729, G723, GSM, etc.) are pervasively used in the emerging VoIP phone calls. It is desired (e.g., for security reason) in many VoIP applications to identify the speaker. This paper investigates an innovative scalable approach to achieve the speaker ID directly from the compressed voice packets. A set of feature vector is first identified and grouped from the compressed voice stream, and then fast clustering mechanism is employed to classify the voice packets for real time speaker identification.

By: Charu Aggarwal, David Olshefski, Debanjan Saha, Zon-Yin Shae, Philip S. Yu

Published in: RC23499 in 2005


This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.


Questions about this service can be mailed to reports@us.ibm.com .