Channel Compensation for Forensic Speaker Identification Using Inverse Processing

Barinov A, Koval S, Ignatov P, Stolbov M. Channel Compensation for Forensic Speaker Identification Using Inverse Processing. In: AES Conference: 39th International Conference: Audio Forensics: Practices and Challenges. Audio Engineering Society; 2010. Paper 2-3. Available from: https://aes.org/publications/elibrary-page/?id=15495

@inproceedings{Barinov2010_15495,
  author = {Barinov, Andrey and Koval, Sergey and Ignatov, Pavel and Stolbov, Mikhail},
  title = {{Channel Compensation for Forensic Speaker Identification Using Inverse Processing}},
  booktitle = {AES Conference: 39th International Conference: Audio Forensics: Practices and Challenges},
  note = {Paper 2-3},
  year = {2010},
  month = jun,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=15495}
}

TY  - CPAPER
TI  - Channel Compensation for Forensic Speaker Identification Using Inverse Processing
AU  - Barinov, Andrey
AU  - Koval, Sergey
AU  - Ignatov, Pavel
AU  - Stolbov, Mikhail
T2  - AES Conference: 39th International Conference: Audio Forensics: Practices and Challenges
M1  - Paper 2-3
PY  - 2010
DA  - 2010/06/06
UR  - https://aes.org/publications/elibrary-page/?id=15495
PB  - Audio Engineering Society
LA  - en
AB  - Typically, speaker identification examination requires two audio recordings: a voice sample and a questionable recording. The questionable one is in most of the cases the intercepted or recorded phone call. As far as mobile phones became the most popular way of communication, the biggest part of questionable recordings comes from GSM channels. They use special algorithms and devices to transmit the speech signal through GSM channel, but these devices and algorithms change the original signal, thus the possibility of usage of such a recording for speaker identification becomes doubtful. In this paper we study how GSM channel changes the formants position (frequencies) of speech signal and how inverse filtration helps to compensate this influence of channel on speech signal and on forensic speaker identification performance.
ER  -