J. Bitzer, C. Rollwage, and M. Neumann, “Evaluation Results of Speaker Verification for VoIP Transmission with Packet Loss,” in Proc. AES Conference: 54th International Conference: Audio Forensics, Jun. 2014, Paper 2-3. [Online]. Available: https://aes.org/publications/elibrary-page/?id=17329
Bitzer J, Rollwage C, Neumann M. Evaluation Results of Speaker Verification for VoIP Transmission with Packet Loss. In: AES Conference: 54th International Conference: Audio Forensics. Audio Engineering Society; 2014. Paper 2-3. Available from: https://aes.org/publications/elibrary-page/?id=17329
@inproceedings{Bitzer2014_17329,
author = {Bitzer, Joerg and Rollwage, Christian and Neumann, Martin},
title = {{Evaluation Results of Speaker Verification for VoIP Transmission with Packet Loss}},
booktitle = {AES Conference: 54th International Conference: Audio Forensics},
note = {Paper 2-3},
year = {2014},
month = jun,
publisher = {Audio Engineering Society},
url = {https://aes.org/publications/elibrary-page/?id=17329}
}
TY - CPAPER
TI - Evaluation Results of Speaker Verification for VoIP Transmission with Packet Loss
AU - Bitzer, Joerg
AU - Rollwage, Christian
AU - Neumann, Martin
T2 - AES Conference: 54th International Conference: Audio Forensics
M1 - Paper 2-3
PY - 2014
DA - 2014/06/06
UR - https://aes.org/publications/elibrary-page/?id=17329
PB - Audio Engineering Society
LA - en
AB - "In this contribution we show the influence of Voice over IP (VoIP) transmission for the task of forensic speaker verification if packet loss occurs. We particularly tested the influence of packet loss up to 20% on two modern automatic speaker verification systems with different feature sets. One of the systems was our own development to control features and the classifier parameters. The other one was a commercial system used in the forensic field. Furthermore, a phonetic acoustic analysis of the formant deviation and its influence on speaker verification is given. The results indicate that packet loss up to 20% has only minor influence on the performance of modern computer-based speaker verification tools and that the changes of the formant frequencies are not significant. However, some dynamic formant transitions get lost at high packet loss rates."
ER -