CSR: Speaker Recognition from Compressed VoIP Packet Stream

Charu C. Aggarwal, David P. Olshefski, Debanjan Saha, Zon-Yin Shae, Philip S. Yu

Abstract

VoIP applications require the ability to identify speakers in real time. This paper presents compressed speaker recognition (CSR), an innovative approach to perform speaker recognition directly from the compressed voice packets. CSR performs online speaker recognition from live packet streams of compressed voice packets by performing fast clustering over a defined subset of the features available in each compressed voice packet. Our experimental results show that CSR is highly scalable and accurate across a broad range of speakers
BibTeX
@inproceedings{aggarwal2005csr,
  author = {Charu C. Aggarwal and David P. Olshefski and Debanjan Saha and Zon-Yin Shae and Philip S. Yu},
  title = {{CSR: Speaker Recognition from Compressed VoIP Packet Stream}},
  booktitle = {ICME},
  year = {2005},
  doi = {10.1109/icme.2005.1521586},
}

Loading related content...

Figure