Voice Identification Standards: Practical and Official

As an audio forensic expert who conducts voice identification, I receive calls from people around the world asking about voice identification. The American Board of Recorded Evidence provides voice identification standards that help me determine if I can identify a piece of audio evidence.

Some of the requests I receive are a stretch because the audio in question does not have enough words spoken in order for me to create an exemplar.  An exemplar is one of the most important tools to a voice identification test.  The exemplar must be made as closely to the original recording as possible.  The audio forensic expert often does not have as much control over the technology when making the exemplar as they would like.  In that case careful attention must be paid to the variable electronic readings in spectrograph measurement allowing or compensating for the variable.

In other words, if a piece of audio evidence was a telephone intercept or voice mail recording, the exemplar must be made using a telephone and recording device as similar as possible to the device that was used to create the original recording in question. This is where the attorney representing our side in the litigation comes in.  The attorney must petition the court during discovery to help the audio expert learn what equipment was used to record the original evidence.

This process was especially important back in the analogue days. Today’s digital recordings create much higher quality recordings and have different authentication processes.
Here are the American Board of Recorded Evidence voice identification requirements as accepted in the scientific community:


Standards for Comparisons Determination


The following are the standards accepted nationally by all professional organizations involved with voice identification, including the FBI, the Audio Engineering Society, the International Association for Identification, and the American Board of Recorded Evidence:

• IDENTIFICATION: At least 90% of all comparable words must be very similar aurally and spectrally, producing not less than twenty (20) matching words. The voice samples must not be more than six (6) years apart.
• PROBABLE IDENTIFICATION: At least 80% of the comparable words must be very similar aurally and spectrally, producing not less than fifteen (15) matching words.
• POSSIBLE IDENTIFICATION: At least 80% of comparable words must be very similar aurally and spectrally, producing not less than ten (10) matching words.
• INCONCLUSIVE: Falls below either the Possible Identification or Possible Elimination confidence levels and/or the examiner does not believe a meaningful decision is obtainable due to various limiting factors.
• POSSIBLE ELIMINATION: At least 80% of comparable words must be very dissimilar aurally and spectrally, producing not less than ten (10) words that do not match.
• PROBABLE ELIMINATION: At least 80% of the comparable words must be dissimilar aurally and spectrally, producing not less than fifteen (15) words that do not match.
• ELIMINATION: At least 90% of the comparable words must be very dissimilar aurally and spectrally, producing not less than twenty (20) words that do not match.

To learn more about voice identification, call 800.647.4281

Voice Identification Line Up

Recently, I was asked to listen to 23 phone intercept recordings and determine if any of the voices in these conversations were repetitive.  As an audio forensic expert, when I conduct a voice identification test, I have to have an exemplar or voice sample of the accused.

Back to back voice samples are the first step to a task like this.  Each telephone conversation included two voices. The first thing I did was separate the voices and create two new audio project files. That way I can critically listen to all voices back to back in order to determine if any of the voices were identical or at least had similar characteristics. 

These telephone recordings were created by federal law enforcement and were very clean.  No noise reduction was necessary as it was back in the analogue days.

Once I completed this back to back assembly process, I had the recordings transcribed so I could choose phrases and sentences to use when creating the exemplar.  An exemplar is a known sample of speech recorded as exact as possible to the original evidence.  The exemplar is created under supervision so I know the identity of the person speaking (who is the accused).

When the exemplar recording is complete, those phrases that were recorded are now inserted into the original evidence recordings in the new audio project files for critical listening.  In this particular case, I noticed that the exemplar did match some of the telephone conversation evidence that was recorded by the federal authorities. 

The next step is to create work notes listing all the similarities as well as differences observed during the critical listening phase of the voice identification testing.  These notes help me create my report when the voice identification testing is complete.    

I also use spectrum analysis and sonograms to help with the identification process.  I often print out the display of these two electronic measurement devices and include these print outs with my report. 

One thing I have learned over the 25+ years as a forensic expert is to keep it simple.  Judges like an uncomplicated decision from a qualified forensic examiner.  They become frustrated when they have to interpret new information they have never heard of or are not familiar with.

Voice identification is both an art and a science. As a voice identification expert, I use my talent skill and ability in every case I am assigned to.  The science is acceptable in court and the art is the ability to adapt every case to scientific standards.  

Is It Still Elvis Presley̶? Cast Your Vote

Last Monday I did another radio interview for Elvis Express Radio. Joe from the network called me about 10 am EST and asked how I knew this song had Elvis Presley singing. I explained to him that I did forensic voice identification and compared the vocal to similar types of Elvis songs from around the same time. ‘What Now My Love’ was one of the songs I used as an exemplar, which is the second step when I conduct voice identification. In this case an exact exemplar could not be created for obvious reasons so we went with songs that were recorded around the same time and had similar vocal innovation.

We would like to know what you think about the new song. Do you believe it's Elvis Presley?



Joe from Elvis Express radio told me during my interview that he had been an Elvis fan for 40 years and he believed that “Living to Love You” was not sung by Elvis Presley. I told him that I respected his opinion and we concluded the interview.

I did not think much of it because I have been an audio engineer working with world renowned and local musicians and artists as well as a forensic expert for 27+ years. Of course I could be wrong; there is always a margin of error in any voice identification.

Today I received an email from the lawyer handling the sale of the song. Her update is very interesting. She hired author Tom Grace who is an Elvis expert to listen to the song and review the documents.
Tom has positive feedback regarding my forensic analysis. After he listened to the tape he confirmed that it had to be Elvis for a different reason than my forensic voice analysis determined.

"No one would try to make a tape to sound like Elvis with such a poor arrangement" was his first comment. The instruments were all out of balance including the piano. Tom said he could hear the piano and he believes he knows who the piano player was and who was playing the guitar and base.

He has researched the date and time that everyone was together and came up with February 24, 1965 in Nashville when they were recording the soundtrack for the Elvis movie “Harum Scarum.” There are three recordings documented from 11:00 p.m. to Feb 25 at 1:00 a.m.

He does not know what was recorded other than they worked on one record which was for “Harum Scarum.” The recording was not put on a reel and must have been direct to acetate because there is a popping sound in it. It was not copy written until 1976; a letter to Albert Lee states copy writing does not normally occur until the song is published.

Speculation is that Jimmie Crain heard that Elvis wasn't doing well in 1976, so he checked and found the song had not been previously copy written by RCA . He apparently decided to copy write it before something happened to Elvis.

Tom Grace will be publishing his findings and the lawyer representing the sale of the song, Violet Hinton, has contacted WWMT TV 3 to interview Tom Grace in a follow up story.

If you believe this song is Elvis Presley, hit the like button on the article link on Audio Forensic Expert's Facebook page. You can also email us at Primeau@PrimeauProductions.com.

Clarification for Authentication of Audio Recordings

The following article was written to help the legal community better understand the audio clarification process. The descriptions it includes will also help a lay person better understand the value of audio clarification.

All digital and analogue recordings have a noise floor. The term “noise floor” originated when manufacturers of analogue audio recorders referred to the extraneous noise that their machines created in addition to the desired recorded audio signals.

Often, a background noise constitutes most of the audio recording and covers a portion of speech that needs to be audible in order to determine a series of events pertinent to the case. Noises like the humming of a fan, air conditioning, heating systems, wind, and other unwanted sounds contribute to the audio recording noise floor. These noises can often be removed by the audio forensic expert (who is also known as the examiner) to help determine facts about the series of recorded events.

The extraneous sounds of background noise and noise floor can consist of a heating or air conditioning fan running, refrigerator motor, window fan, clock, fluorescent lighting, wind, rain, the running engine of a car, and even radio or television. All these sounds contribute to the background noise and noise floor of a recording and aid the forensic examiner in authenticating a recording. However, although these sounds can authenticate the environment of an alleged crime, this background noise can interfere with the forensic examination. It is appropriate and part of the forensic examiners job to remove these background sounds in order to authenticate or clarify an exhibit of audio recorded evidence.

Some of the recordings experts are asked to authenticate are confession recordings created by law enforcement agencies. Defendants exclaim, “That is not what I said, they edited it” or “There is more I said that has been edited out of the recording”. Due process entitles both parties in litigation to examine any evidence presented in their case. However, original recordings are not always available for examination. How do you as a law enforcement official feel about the absence of original recordings?

I have worked on cases where missing “original evidence” was considered spoliation of evidence. Personally, I believe that the circumstances of each case should be considered by the forensic examiner before any decision has been made by either party.

If there are noticeable questionable characteristics that the forensic examiner observes regarding the audio evidence, then the expert must notify the officials in charge of the findings during the preliminary examination phase of the forensic investigation. Original recordings are required for litigation cases. If they are not produced, a motion to suppress the evidence should be filed.

A Three Part Process for Audio Restoration

In the following blog post, I will help you understand a basic three part process for audio restoration. In the embedded video, I exhibit an audio file that was lifted from a video which is in need of some audio restoration. The video walks you through the process which varied from video to video in this multi part video training set.

The first step is to either compress the audio increasing the gain during the process or removing any unwanted distortion; whichever you feel is best to lead with. You can try one process first then the second. Worse case you can apply the processes in opposite order if your initial results are not up to your expectation.
Varying the order which filters and noise reduction are applied is how a forensic examiner will proceed when restoring an audio file. Audio restoration takes time, patience and good critical listening skills.

The three filters I will demonstrate in this video are wave hammer, equalization and noise reduction. I use Sony Sound Forge software 9.0 for this example. Other audio software programs can be used and more than likely include similar filters to those found in Sound Forge.

Creating an Exemplar for Voice Identification

An audio exemplar is an audio recording that is created by the audio forensic expert and will be used as a comparison to the evidence for the purpose of identification. Unlike the original evidence, the exemplar is created in a controlled environment. If the original evidence is a telephone recording then the exemplar must be created on the phone as close to the original evidence as possible. If the phone that was assumed to be used to create the evidence is available, that phone should be used to create the exemplar. The goal is to reconstruct as much of the original recording characteristics as possible when recording the audio exemplar.

A transcript of the evidence recording must be created to help guide the exemplar recording process. The forensic expert does not notify the accused (defendant) of the portions of the transcript that will be recorded until the scheduled recording time. The reason for this is to have the ability to be spontaneous and unrehearsed when creating the exemplar.

The exemplar comparison call is scheduled between the lawyer, audio forensic expert and the defendant. If the defendant is incarcerated the prison is involved in the coordination so the call can be recorded from the prison. In this case, the identity of the person delivering the exemplar is known. If the defendant is not incarcerated, then a neutral party or witness must be present to swear to the identity of the person making the exemplar recording. A representative from the court of law enforcement official would be a good witness.

The call is recorded by the audio forensic expert using an electronic telephone interface device manufactured by Gentner. Other companies manufacture similar devices but we use the Gentner SPH 10 in our forensic lab.
We also use Sony Soundforge software to record the exemplar and conduct the voice identification testing.

The call begins with the forensic expert explaining to the defendant the voice tone necessary when delivering lines from the transcript for recording purposes and continues to guide the exemplar recording process. Its best to have the defendant read each sample three times giving the expert options when conducting the testing.

Double check the recording quality by monitoring the telephone recording both during and after the exemplar creating process is complete especially if the defendant is incarcerated.

Once a reliable exemplar has been created, the audio expert can begin the voice identification process. If multiple telephone conversations are submitted as evidence, an exemplar should be created of each conversation.

Creating a high quality exemplar under supervision is probably the most important part of the voice identification process. If there are other recorded conversations that include the defendant’s voice but are not the exact words used in the evidence recording, they can be used as comparison. Be cautious in the voice identification testing as this is not as desirable of a testing as having an exact exemplar. In this case the voice identification expert must rely on their skills to substantiate the reasoning and their conclusion more so than when an exact exemplar has been created.

Original Digital Media Evidence is Mandatory

Digital audio is recorded and stored in electronic equipment. If the audio is needed in court, the original device that created the recording must be identified and kept in a chain of custody. The only exception is when both parties involved in the litigation agree that a copy is sufficient. If there is doubt in the authenticity, the audio expert must refer to the original to support the authentication of the audio evidence.
The reason is that the audio copy has been removed from its original environment and is vulnerable to alteration. In addition, if a computer created the original recording, additional information can be examined by the audio expert such as file creation, last accessed and other computer forensic information that can support the audio evidence authenticity.
If the original audio recording was created in a digital pocket recorder (which many law enforcement officials use) then that original pocket recorder must maintain a chain of custody and become the original evidence. Any external copy created by a number of methods and played outside of the digital pocket recorder is a copy. Unless an audio expert can authenticate the copy (which can be done once the original has been examined) it cannot be used in a court proceeding. If the audio copy has been authenticated by an expert, than it will be easier to play and amplify in the court for a judge and jury.
I have testified in criminal cases for the defense when the client swore under oath that the audio recording had been altered and did not represent the facts as they occurred. Now it’s their word against the other side and when the court has to decide, the prosecution most always, will prevail.
If you have had an experience with audio evidence and would like to share your story, please comment on this post and your story will be heard.