Speaker Identification Technology

Seamless Authentication

Identify speakers instantly and with the highest accuracy based on the unique characteristics of their voice and improve their authentication experiences by reducing unnecessary security passwords.
Increased Security

Add another layer of security to your authentication process without compromising the ease of access by using a voice-based verification that is incredibly accurate, fast, and always available.
Fraud Prevention

Prevent fraud from happening with the system running automatically in the background and marking every suspicious speaker claiming to be one of your clients but not matching their voiceprint.

What People Are Saying

Phonexia's voice biometrics allows contact centre agents, smart IVRs, and conversational AI platforms to verify customers' identities rapidly, securely, and precisely. Its forensic-level precision enables organisations to improve customer journeys, combat fraud, and reduce average handling times and cost to serve.

We have been selling Phonexia products in the Asian market for over 3 years now, and we can clearly say that Phonexia products are by far the best ones in the global market. We have encountered some local and global competitors, but we can easily push them off the table by showing how strong and affordable Phonexia products are. Phonexia’s strength comes from a mixture of dedicated genius engineers and down-to-earth, smart business experts who can draw big pictures.

Technology Details

• Allows you to perform fast 1:1 speaker verification, and 1:N and N:M speaker identification
• Is language-, accent-, text-, and channel-independent
• Uses deep neural networks, called Deep Embeddings™, to generate highly representative mathematical models of the human voice, called voiceprints, offering extremely high speaker recognition accuracy and speed
• Applies state-of-the-art channel compensation techniques, verified by NIST evaluation, compatible with the broadest range of audio sources possible: GSM/CDMA, 3G, VoIP, landlines, satellite phones, etc.

Input Requirements

• WAV or RAW (PCM unsigned 8 or 16 bits, IEEE float 32-bit, A-law or Mu-law, ADPCM), FLAC, OPUS; 8 kHz+ sampling (other audio formats are automatically converted)
• Recommended Speech Length for Enrolment: 20+ seconds
• Recommended Speech Length for Identification: 7+ seconds (can be shorter after a calibration)
Output Formats

• XML/JSON format with all results
• Results files with a log-likelihood ratio (-∞;∞)
• Percentage metric scoring <0-100%>
Supported Languages

Identifies speakers in any language as the technology is language independent.

Join Us for a Free Demo

Schedule a demo with our experts and see for yourself how Phonexia Speaker Identification technology can help your business.

We will show you a free online demo tailored to your needs, showcasing Phonexia speech and voice recognition technologies and the ways you can use them to achieve your project’s goals.

Speaker Identification

Seamless Authentication

Increased Security

Fraud Prevention

Input Requirements

Output Formats

Supported Languages

What Will You Get?

We will contact you shortly and arrange a time suitable for you.