Checkout
Phonexia Voice Inspector
Phonexia Voice Inspector

PHONEXIA VOICE INSPECTOR

Phonexia Voice Inspector (VIN) provides police forces and forensic experts with a highly accurate speaker identification tool that supports criminal investigations. It uses the latest voice biometry algorithms to recognize a speaker automatically.

Selected Features:-
 
  • 1:1 identification and 1:n identification
  • Automatic speaker identification tool to strengthen the results of standard phonetic-based approaches
  • Phoneme recognizer for the searching and visualization of the same phoneme sequences across audio files
  • Evaluation tool for the measurement of accuracy in users’ data sets
  • Waveform editor with tools such as a spectrum panel, voice activity detection, and more
  • Simple management of investigation cases

 

 

Technology:-

 
  • Phonexia Voice Inspector is independent of language, accent, text, and channel
  • Uses a Gaussian Mixture Model (GMM) with powerful techniques (an iVector based system, etc.) to generate small but highly representative voiceprints
  • Applies state-of-the-art channel compensation techniques, verified by NIST evaluation
  • Compatible with the widest range of audio sources possible (applies channel
  • compensation techniques): GSM/CDMA, 3G, VoIP, landlines, etc.
 
Input:-
 
  • Input format for processing:
WAV or RAW (8 or 16 bit linear coding), A-law or Mu-law, PCM, 8 kHz+ sampling
  • Minimum speech signal for enrollment:
recommended 45+ seconds
  • Minimum speech signal for identification:
recommended 10+ seconds
 
Output:-
 
  • Scoring to likelihood ratio (LR), log-likelihood ratio (LLR) and verbal presentation of results
  • Graphic presentation of likelihood ratio (LR)
  • Detailed report output (expert opinion template automatically generated) for presentation of results (to court or an investigation team)
 
 
 
Recent Publications
 

Publication: Eliciting and evaluating likelihood ratios for speaker recognition by human listeners under forensically realistic channel-mismatched conditions

Publication: Evaluation of a forensic automatic speaker recognition system with emotional speech recordings

Publication: Automatic speaker recognition performance with matched and mismatched female bilingual speech data

 
Price from: On application
Out of Stock

« Previous | Next »

Subscribe to our mailing list