Solutions by VoicePIN.com

Voice Biometrics

VoicePIN Voice Biometrics is a new technology and increasingly used tool in the process of user authentication, which not only shortens the user verification, but also increases the safety.

Virtual Agent Dronn

VoicePIN Dronn is a virtual person represented by intelligent computer system that communicates with the client by voice. It replaces a live consultant in interacting with clients. The system is used to support telecommunication customer service, like Contact Center systems.

Voice Predictive Analitycs

VoicePIN Predictive Analytics is the new system, which predict customer behavior and can create users profile. The system collects BIG DATA from ASR, NLP and voice biometrics. This kind of client analyzes influence the increase in sales.

AntiFraud

VoicePIN AntiFraud is a set of tools that effectively detect fraud attempts in customer voice systems, such as call centers, hotlines and video calls.

Voice Biometrics

Voice Biometrics is a new technology and increasingly used tool in the process of user authentication, which not only shortens the user verification time by more than four times, but also increases the safety of this process.

 

Our solution’s specifications:

 

○ Contrary to the password, which can get into unauthorized hands, the voice is unique for every human being. This ensures that the users’ data are adequately protected and can be accessed in a quick and comfortable way. Conventional, widely used PIN or password based authorization method is not only uncomfortable for users, but also costly.

○ Voice recognition solution is used for authentication, login, personalization, fraud detection on mobile apps, helplines, call centers.

How it works?

 Voice Biometrics Technology is based on analysis of the distinctive patterns contained in the human voice, impossible to reproduce.

A voiceprint is made of user’s voice patterns that are stored in the form of mathematical models.

VoicePIN is resistant to spoofing. It detects whether the sample is an original or a re-played recording.

Each time a speaker is being authorized, recording is verified and matched with all previously collected data guidelines.

VoicePIN is robust to perceived voice changes. It works even when you have a cold or a sore throat. What VoicePIN listens to in your voice, is not what people hear in it.

Virtual Agent Dronn

 

VoicePIN Virtual Agent Dronn is a virtual person represented by intelligent computer system that communicates with the client by voice. It replaces a live consultant in interacting with clients. The system is used to support telecommunication customer service, like Contact Center systems.

 

Our solution’s specifications:

 

○ Replaces the consultant in call center

○ Based on speech recognition technology (ASR) and speech synthesis (TTS), natural language processing (NLP), semantic analysis (SA)

○ Full compatibility with voice biometrics systems

○ Examples of application: debt collection process, customer segmentation, marketing questionnaires, fatca, credit card applications, communication damage notification, appointment to a doctor, notification of power failure

○ Realistically reduces the consultant’s cost and increases the effectiveness of processes (up to 85%)

○ Further stage of development – predictive analytics

Dronn’s benefits:

Voice Predictive Analitycs

 

VoicePIN Predictive Analytics is the new system, which predict customer behavior and can create users profile. The system collects BIG DATA from ASR, NLP and voice biometrics. This kind of client analyzes influence the increase in sales.

Value

 

○ VPA improves sales in voice channels (call centers, IVR, virtual voice agents)

○ VPA improves fraud detection in voice channels

○ System recognize unknown caller

Our solution’s specifications:

Based on Voice biometrics technology (voice authentication, speaker recognition)

Language-independent

Multichannel

Text-dependent verification - ACTIVE

Text-independent verification - PASSIVE

Antifraud (fraud discovery, voice conversion, liveness detection, playback detection)

Platform-independent, REST API

Architecture: on-premise or cloud (easy to test)

Our solution resolves 2 problems:

●The average user has 21 passwords for banking accounts, Internet services, mobile applications. People hate to remember passwords and PIN numbers and recall last invoice number or mother’s maiden name (CUSTOMER EXPERIENCE)

●Traditional passwords and PINs are increasingly easier to hack (SECURITY)

AntiFraud

Passive identity verification to verify that the voice of the customer corresponds to the voice recorded during previous conversations. The consultant, seeing the level of similarity of the voice of the caller, can react appropriately and lead the conversation while the caller does not know that is additionally verified. VoicePIN AntiFraud is populated with fraudsterand customer voiceprints. This is optimal scenario with full capabilities to detect frauds.

 

Our solution’s specifications:

 

○ VoicePIN Flow The system checks if the client’s voice matches to voiceprints from previous conversations and uses a passive identity verification. In real-time, a consultant can track the level of similarity of a customer’s voice by comparing it to his or her previous recordings. The consultant also has the ability to react and make the call so that the caller does not know that he/she is being checked additionally.

 

○ VoicePIN  Blacklist Blacklist of users is available for text-independent mode (TI). This element allows for quick recognition of conversations in which the voice of a known scammer is breaking into other accounts. In addition, it is possible to create separate Blacklists for different processes and channels.

 

○ VoicePIN Fraud Discovery – This feature allow to create new voice patterns for Blacklist based on the known fraud calls database, from which the most common voices are captured. This component makes it much easier to create a Blacklist by automating the process of grouping recordings and finding the most effective models of fraudster. The tool analyzes the collection of historical recordings previously identified as actual fraudster and reproduces repeated voices of serial fraudster. The result is a list of proposed new voices added to the Blacklist.

 

○ Emotion Recognition The function allows to detect situations where the caller is:

  • anxious

  • aggressive

  • grotesque

  • adventurous

  • angry

How it works?

 

Increase Customer Experience, Security, 
Sales and Fraud Detection!

 

For more information about our solutions – contact us.