Voice Identification & Speaker Comparison

Voice Identification & Speaker Comparison analysis is based on the premise that every voice is individually characteristic enough to distinguish it from others. Factors contributing to voice uniqueness include the size and configuration of the throat, nasal and oral cavities, and the shape, length, and tension of the vocal cords.  Another factor in determining voice uniqueness lies in the manner in which the articulator muscles are manipulated during speech.

Stutchman Forensic Lab conducts Voice Identification & Speaker comparison analysis using two methods: the Aural/Spectrographic Method and Biometric Speaker Identification.

 

Aural/Spectrographic Speaker Comparison

Aural/Spectrographic speaker comparison is a combination of aural (listening) and instrumental comparison of one or more known voices with an unknown voice for the purpose of identification or elimination. Factors which are compared are resonance quality, pitch, temporal factors, inflection, dialect, articulation, syllable grouping and peculiar speech characteristics.

Aural/Spectrographic analysis has been a scientifically accepted method of speaker comparison in the United States legal system since the 1960’s. With the advent of the digital age and the exponential power of computer processors in recent years, Biometric voice analysis is quickly becoming a more viable method of forensic voice comparison.

Biometric Voice Identification & Speaker Comparison

Biometrics refers to the quantifiable data (or metrics) related to human characteristics and traits. Biometrics are used for identification of humans by their unique characteristics. This type of analysis is used in DNA testing, fingerprints, facial recognition, palm prints, iris recognition, and voice/speaker identification analysis. Biometric voice identification is used by federal agencies including the FBI, NSA, CIA, etc.

Biometric voice analysis uses Pitch Statistics, Spectral-Formant Method, and Gaussian Mixture Models (GMM) to compare voice samples. Biometric voice analysis differs from the Aural/Spectrographic method in that it requires a significant amount of computing power and relies more heavily on statistical data which is processed by a computer than the findings of a human analyst.

Want to learn more about the history and science of Forensic Voice Identification & Speaker comparison? Click here to view our full, in-depth article on the subject.

As experienced expert analysts, our highly trained and qualified forensics team uses top of the line hardware and software technology to carefully handle and thoroughly analyze your evidence audio, video, and photographic media. We can isolate, separate, enhance, and authenticate all relevant aspects of audio and video recordings in order to produce expert evidence backed by many years of master experience. As an expert witness in the courtroom, our testimony from the witness stand will contain provable facts and relevant demonstrative evidence that can often make or break a case (see our Testimonials).

Let us serve you. Contact Us at (800) 799-0828