SESTEK Forensic Voice Analysis is an advanced voice biometrics solution used for law enforcement and criminal identification. It helps forensics experts and security organizations complete voice treatment and speaker identification processes accurately. With the straightforward identification it provides, Forensic Voice Analysis contributes to criminal investigation and prosecution of suspects.

Why SESTEK Forensic Voice Analysis?

SESTEK Forensic Voice Analysis is a fast and easy-to-use audio forensics tool that provides the following advantages:

  • Accurate identification of a speaker from his or her voice
  • Precise and reliable identification/verification results
  • Comprehensive forensics reports
  • An assistive solution that facilitates experts’ work by saving them hours previously spent listening to audio recordings

Features

  • Text independent comparison
  • Intuitive graphical interface
  • Ability to listen to and analyze audio recordings via software interface
  • Ability to compare multiple audio recordings automatically
  • Ability to detect speech and non-speech sections in an acoustic signal
  • Ability to compare audio recordings obtained from different channels such as microphones or telephones
  • Ability to separate speakers’ voices in a mono recording
  • Ability to identify the gender of a speaker through acoustic signal
  • Ability to archive applied analysis
  • Compatibility with Windows operating system

Modules

Forensic Voice Analysis includes the following modules:

  • Likelihood Ratio (LR) Calculation enables one-to-one comparison of two audio files and generates statistical scores and probability distribution graphics that can be used as evidence.
  • Speaker Identification confirms or disproves the identity of individuals based on audio files used during investigations.
  • Formant Verification enables one-to-one comparisons of formant distributions of audio recordings.
  • Speech-Silence Detection enables the automatic detection of speech and non-speech sections in the audio and makes it possible to check the labels of the system and manually apply corrections.
  • Speaker Diarization is the detection of who spoke when in a single channel recording of speech.
  • Gender Identification automatically detects the gender of the speaker in the audio.

SESTEK is featured in DMG Consulting’s 2016 Voice Biometrics Product and Market Report. The report analyzes market trends and challenges. It reviews product innovation and competitive landscape. It also presents market activity data with five-year projections.

The report reviewed SESTEK Voice Biometrics technologies in terms of omni-channel capabilities, enrollment authentication methods, fraud/risk management approach, and value-added capabilities. SESTEK develops voice biometrics technologies with the aim of increasing efficiency by reducing costs and making life more convenient by providing practical solutions. To learn more about “The 2016 Voice Biometrics Product and Market Report,” please click here.