BATVOX
Definition
A commercial automated speaker recognition system (originally Agnitio, later Nuance Communications) widely used in operational forensic casework in Europe and Latin America. Produces LR outputs from i-vector or x-vector embeddings via PLDA backends.
- Type
- Automated speaker recognition system
- Original developer
- Agnitio
- Later owner
- Nuance Communications
- Output
- Likelihood ratio from i-vector/x-vector embeddings via PLDA
Common questions
How does BATVOX's output differ from a human examiner's opinion on voice similarity?+
It produces a quantified likelihood ratio derived from statistical embeddings and a trained scoring backend, giving a numerical strength of evidence rather than a categorical opinion, which aligns it with the broader move toward likelihood-ratio reporting in forensic voice comparison.
Where has BATVOX seen the most operational use?+
It has been widely deployed in casework across Europe and Latin America, often supporting or complementing auditory-acoustic phonetic analysis rather than replacing it, since automated systems and traditional phonetic comparison are generally used together to strengthen a conclusion.
Related terms
- 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,...
- 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...
- ENFSI BPM
- The ENFSI Best Practice Manual for Forensic Comparison of Speech (2015, rev. 2022); the operational standard for speaker comparison in European forensic...
- 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...
- 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....
- NIST SRE (Speaker Recognition Evaluation)
- A competitive benchmarking series run by the National Institute of Standards and Technology since 1996, in which research and commercial teams submit...
- PLDA (Probabilistic Linear Discriminant Analysis)
- A statistical back-end model used with i-vector and x-vector systems to compute a similarity score between two utterance representations, normalised for within-speaker...
- X-Vector
- A deep-learning speaker embedding produced by the penultimate layer of a time-delay neural network (TDNN) trained for speaker classification. Introduced by Snyder...