Channel Compensation for Forensic Speaker Identification Using Inverse Processing
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.
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is temporarily free for AES members.