Voice Inspector

Voice Inspector Introduction

Phonexia Voice Inspector (VIN) is a powerful tool designed by Phonexia for forensic experts and law enforcement agencies to assist in criminal investigations through highly accurate speaker identification. It performs automatic forensic voice comparisons in compliance with the ENFSI guidelines and helps prepare comprehensive case reports for court proceedings.

Top Three Benefits of Using Voice Inspector

• Reduced Investigation Time – Enhance the forensic expert’s conclusions with accurate, unbiased voice analysis.
• Efficient Voice Analysis – Identify speakers in recordings of any language with minimal language-specific expertise.
• Detailed Reports – Automatically generate reports containing all necessary details for case documentation.

Voice Inspector software utilizes an extremely accurate voice biometrics engine to automatically compare speakers’ voices and identify multiple speakers in recordings.

Advantages of Voice Inspector

• Advanced automatic voice-print analysis based on Deep Neural Networks (x-vector), providing highly precise speaker identification.
• Simple installation, intuitive GUI, clear result interpretation, customizable reports, and efficient case management.
• Easily adaptable for use in any country through the integration of a population database.
• Possibility of portable licensing via USB dongle.
• Integrated SID Evaluator for easy software testing and validation.

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 enrolment: 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)