Today, more than any other time in the history of the United States and the world, we find our court systems full of digital audio files in the form of evidence. As an audio forensic expert, I have testified in many cases in the United States and worked on cases in India, Turkey and France. One thing I see time and time again, regardless of geography, is the misunderstanding of how voice identification can aid in litigation.
The American Board of Recorded Evidence here in the United States has established a probability factor with regard to voice identification. This board is a part of the American College of Forensic Examiners International.
When conducting a voice identification test, I look for spectrums that match the recording in question against the exemplar.? An exemplar is a comparison recording that a forensic expert creates of the voice in question for comparison purposes. Does each recording include spectrums that are similar?
Even more important are the words themselves. The way the words are pronounced, the pacing of the words pronounced, the space between the words, the articulation of the words and the consistent delivery style are all considered.
No two human voices are the same just like no two fingerprints are the same. Despite attempted voice disguise cover up, a trained forensic expert can identify a voice and compare it to another voice to determine identification.
With experience, a trained audio forensic expert can use voice identification skills in a variety of ways and help uncover the truth behind audio recordings.
In recent months I have used traditional voice identification techniques to identify a new Elvis Presley song, singer in a motion picture soundtrack as well as confirm the difference between a father’s and son’s voice for a civil litigation.
Some would say this is not a proper way to conduct voice identification testing. However, in my humble opinion, with 28+ years of voice identification experience, I believe as long as the audio forensic examiner has experience, an exemplar that is as exact as possible and the necessary tools (hardware and software), nontraditional voice identification is possible.
Using the new Elvis Presley song discovery, turns out that I was right with my positive identification. Two Elvis Presley historians agree with me that this new song is indeed Elvis Presley. After I completed my voice identification testing his record company came forward and confirmed the session date and time the recording was made.
The bottom line is that going forward, voice identification will continue to be an important part of the litigation process when audio evidence is involved.? The science is as exact as the expert is experienced.? The more experienced the expert, the more solid the expert’s report.