ENFSI BPM
Definition
The ENFSI Best Practice Manual for Forensic Comparison of Speech (2015, rev. 2022); the operational standard for speaker comparison in European forensic laboratories, requiring LR reporting, validated methodology, representative background databases, and ISO 17025 accreditation.
- Scope
- Covers forensic speaker comparison and facial image comparison with separate standards for each
- Core requirement
- Likelihood ratio reporting is the required framework for delivering expert conclusions in both speaker and facial image comparison
- Geographic reach
- Operational standard for ENFSI member laboratories across Europe
- Accreditation link
- Requires ISO 17025 accreditation as part of compliance
Common questions
What is the ENFSI BPM?+
The ENFSI (European Network of Forensic Science Institutes) Best Practice Manual is a set of standards for forensic comparison work. It covers speaker comparison and facial image comparison, defining how European forensic labs must conduct and report these analyses. The manual requires use of likelihood ratio reporting rather than older subjective methods.
Do forensic labs have to follow the ENFSI BPM?+
ENFSI member laboratories in Europe are required to follow the Best Practice Manual as their operational standard. The manual demands validated methodology, use of representative background databases for comparison, and ISO 17025 accreditation. It sets the reporting framework that labs must use when delivering expert conclusions.
What methods does the ENFSI BPM define for facial comparison?+
The manual establishes a three-method framework for facial image comparison. These are morphological comparison, photo-anthropometric methods, and superimposition. Analysts use a verbal likelihood ratio conclusion scale when reporting their findings.
Related terms
- AFRS (India)
- Automated Facial Recognition System, the face recognition module within India's CCTNS, operated by the NCRB and used for searching against mug shots,...
- Background Population Database
- A corpus of speaker recordings used to calibrate the LR in a forensic comparison. Must be matched to the case in language,...
- BATVOX
- A commercial automated speaker recognition system (originally Agnitio, later Nuance Communications) widely used in operational forensic casework in Europe and Latin America....
- C_llr (Log-Likelihood Ratio Cost)
- A proper scoring rule measuring the calibration quality of a speaker recognition system's LR outputs; a well-calibrated system has C_llr close to...
- Daubert Standard
- The US federal evidentiary standard (Daubert v. Merrell Dow Pharmaceuticals, 1993) requiring that expert testimony be based on scientifically valid methods with...
- Deep Convolutional Neural Network (DCNN) Embedding
- The face descriptor produced by a neural network trained to map face images into a metric space where same-person images cluster together;...
- ENFSI Verbal Scale
- A standardised table published by the European Network of Forensic Science Institutes that maps ranges of LR values to verbal expressions of...
- Equal Error Rate (EER)
- The point on a classifier's detection error tradeoff curve where the false accept rate equals the false reject rate. Lower EER indicates...
- False Positive Identification Rate (FPIR)
- In 1:N identification, the rate at which a probe image of an individual not in the gallery generates a top-rank match. Critical...
- Formant
- A resonance peak in the vocal tract filter; F1 and F2 together characterise vowel quality (height and frontness), while F3 and higher...
- Frye Standard
- The US legal test for admissibility of scientific evidence, originating from Frye v. United States (1923), which required that a technique be...
- I-Vector
- A fixed-length low-dimensional speaker representation extracted by projecting a speaker's UBM statistics into a total variability space. Introduced by Dehak et al....
Explained in these topics
- Face Recognition: NIST FRVT, FBI NGI and Forensic Facial ComparisonThe European Network of Forensic Science Institutes Best Practice Manual for Facial Image Comparison (2018), which defines the three-method framework (morpholo...
- Modern Automated Speaker Recognition: NIST SRE and the ENFSI BPMThe ENFSI Best Practice Manual for Forensic Comparison of Speech (2015, rev. 2022); the operational standard for speaker comparison in European forensic labora...
- Spectrographic Voiceprint History and Its Modern RejectionThe European Network of Forensic Science Institutes Best Practice Manual for Forensic Comparison of Speech (2015, revised 2022), which codifies the likelihood...