fbpx
v

Speech Automation

N

Multi-Factor Authentication

=

Request a Demo
Sun – Closed

Contact Us
24/7 online feedback

The Intersection of Artificial Intelligence and Human Speech

The Intersection of Artificial Intelligence and Human Speech

Artificial Intelligence is a buzz word in tech because it has unlimited potential to transform the human experience. It’s especially relevant in 2020, as the keyword dominates Google searches and news outlets, including Forbes’ list of technology trends.

What is Artificial Intelligence?
AI is a segment of computer science that focuses on emulating human attributes. It’s the things we take for granted as human beings: listening and comprehension, sight, movement/ grabbing/ manipulation and reasoning with the world.

How Do Artificial Intelligence & LumenVox Intersect?
LumenVox offers artificial intelligence business solutions in two main ways:

The original LumenVox speech recognition software utilized Hidden Markov Models (HMMs) to decipher speech from the sound waves recorded. Hidden Markov models are simplified probability models that work very well in guessing what words are when heard. For example, if the first sound heard is likely to be “Duh” then, in English, it is very unlikely that the next sound will be an “Ess.” But it is very possible that the next sound will be, perhaps, “Oh” as in the word “Doughnut.” Overlaying the sounds, with the probability model of English that speech scientists developed, has produced a very good quality speech recognizer. But in recent years Hidden Markov Models have been replaced by Deep Neural Networks (DNNs). Deep Neural Networks are still probability models; however, they do not contain explicit knowledge of the likelihood of sounds or words in close proximity. Instead, Deep Neural Networks are brute-force models that emerge from “deep” analysis of very large data sets. They record connections for which we may have no explanation. From millions of examples of speech, they extract more complex, irregular, and idiosyncratic statistical rules about sounds, as actually spoken by people, than would be practical to represent in a Hidden Markov Model. LumenVox now utilizes Deep Neural Networks in our passive engine to provide state of the art results in speaker verification and recognition.

Voice Biometrics, aka Voiceprints, make a judgement on whether someone really is who he/she claims to be. With voice biometrics an initial voiceprint is created, in a secure manner, that validates the person’s identity. In future verification attempts, the person’s voice is compared to the original voiceprint. Voice Biometrics are a useful form of AI because they can replace human judgment, prevent human error and be hyperalert to threats with a highly accurate algorithm.

How Can Artificial Intelligence Protect You?
If a fraudster calls a business and claims to be Joe Smith, the agent might ask him a few questions to verify his identity. If the putative Joe is an experienced scammer, he may have researched these questions and prepared answers. Using a voiceprint, however, removes this risk since it is nearly impossible to fake a human voice effectively. Instead of allowing the fraud actor access, the intelligence of the machine exceeds the intelligence of a human agent and fraud is detected.

LumenVox’ aim is to safeguard both businesses and customers using artificial intelligence and the human voice, to take two complexities and make an interaction that is simple yet secure.

Contact us today to learn more.

Spotlight on Active Authentication During Genesys AppFoundry Partner Demo Battle

Spotlight on Active Authentication During Genesys AppFoundry Partner Demo Battle

Last month LumenVox had the honor of being selected as one of only 8 Genesys Appfoundry partners to compete in the Genesys Appfoundry Partner Demo Battle in Amsterdam at G-Summit Europe. While we may not have walked away with the title of “AppFoundry App of the Year,” with over 25 AppFoundry partners in attendance and many more that had applied to participate in the battle, LumenVox was extremely proud to snag a close third for our presentation on active voice biometric authentication for Genesys PureCloud!

For those who couldn’t attend the event and see us participate in the Genesys Appfoundry Partner Demo Battle, you can read the highlights below:

During our 7-minute chance to shine, the LumenVox team was able to briefly share:

  • A demonstration of LumenVox Active Authentication in the Genesys PureCloud environment
  • Key features about the technology behind LumenVox Active Voice Authentication for Genesys PureCloud, including:
    • Signal processing and speech modeling algorithms that are state-of-the-art
    • Customizable text-dependent phrases (e.g. “My voice is my password at ABC Bank”) that are text-prompted for liveness detection
    • The capability to run on servers with mobile client for flexible deployment
    • Flexible integration – web services including support for both SOAP and REST
    • Out-of-the-box tuned language packs for major languages
    • Multiple channel integration, allowing for very board application scenarios
    • 1:1 Authentication and 1:N identification
  • Use cases that are ideally suited for active voice biometric authentication:
    • Password Reset – A common IT helpdesk task that is easily automated, yielding high ROI
    • IVR Self-Service – Modernize your IVR Applications using voice biometrics to reduce friction and secure validation
    • Agent Caller Interactions – Increase both customer and agent satisfaction by authenticating callers using their voice
  • And, a bit about who we are – LumenVox is a global speech automation and authentication company that holds over 85 key industry patents with quick startup/immediate impact solutions designed to:
    • Increase employee efficiency
    • Improve customer experiences
    • Provide highly accurate and convenient voice biometric authentication to keep fraudsters out

If you have any questions about LumenVox Active Authentication for Genesys PureCloud and how your organization can benefit from reduced fraud and enhanced customer experience, we invite you to email us at GenesysSales@LumenVox. You may also watch our latest webinar here, read our latest guest post on the Genesys blog here, or visit the LumenVox listing in the Appfoundry Marketplace.

Card Reader Fraud – A Warning

Card Reader Fraud – A Warning

Everyone in security knows the 3 factors of authentication: something you know (like a password), something you have (like a smartphone or card reader) and something you are (like a fingerprint). But today, very few banks use all 3 factors for online security. And many, still rely on card readers as the something you have token. Card readers typically require you to insert your bank card, enter your PIN, and then report the 6 digit code displayed on the reader.

As the second authentication token, the card reader is critical to online security. So it was with some considerable concern that the following warning is now being issued after being logged into the Royal Bank of Scotland’s online banking:

Have you been asked to use your card reader and provide codes generated by it to someone over the phone? STOP!

Remember:

– We will NEVER ask you for a card reader code to stop or verify transactions over the phone, if you are being asked to share this code over the phone, it’s fraud.

– You should NEVER log onto Digital Banking whilst sharing your screen with someone else. If you are being asked by companies you trust, such as your internet provider, to log in to your Digital Banking while sharing your screen, it’s fraud.

RBS is warning that it is possible to compromise the “something you have” token by spoofing the customer with fake news about his or her account. The vulnerable customer discloses the secret code from the card reader thereby enabling a potential theft from their account.

While knowledge can be stolen and physical tokens compromised by criminal manipulation, it is much harder to obtain biometric data (something you are). A determined thief, with access to things you touch, might be able to extract a fingerprint. But it’s hard work. And it is dangerous since the thief will need to enter your home or office to get at the print. Voice biometrics and facial recognition are much harder to steal. A good voice authenticator or a face recognizer will look for signs of liveness, and your identity, that makes it just too hard to break in.

It’s time the banks get serious about protecting us customers and adopt an effective way to recognize something you are. To learn more, download our product information sheet and/or contact us today.

Top Five Voice Biometric Authentication Trends

Top Five Voice Biometric Authentication Trends

Earlier this summer, LumenVox was a proud sponsor at the Opus Intelligent Authentication Conference in Munich. While the event featured a plethora of information to aid organizations in better understanding how authentication, identification, and fraud prevention technologies in enterprise voice and digital channels can stop fraudsters, build customer loyalty, and enable simple, trusted digital commerce, the top five voice biometric authentication trends were clear to us:

  1. It’s all about fraud – In a world where data is a valuable commodity, criminals are acting in increasingly sophisticated and organized way to be able to steal and abuse that data. The advent of chip cards, for example, has made credit card fraud much harder, and criminals are going after what they see as ‘soft targets’ – such as call centers. According to Forrester, on behalf of Neustar Mitigate Fraud And Consumer Friction with Integrated IDV 2019 study, 61% of surveyed firms had seen an increase in identity theft fraud in the preceding 12 months. According to a 2019 study, 50% of fraudulent account takeover attempts in the financial services sector come through the call center and 23% in the non-financial services sector. LumenVox, recognizing that the threat landscape is evolving, offers a Fraud Detection solution that utilizes advanced voice biometric algorithms coupled with state-of-the-art neural networks to alert fraud teams to suspicious calls in real-time.
  2. It’s all about the customer – Customers are becoming increasingly frustrated with lengthy or inconvenient authentication processes. According to a 2019 study, 46% of respondents were frustrated with authentication processes, versus 31% the previous year. LumenVox’s Multi-Factor Authentication offering is designed to counter that frustration through seamlessly and securely authenticating customers in a manner which ensures the customer experience is excellent.
  3. Voice biometrics is moving into the B2C marketLloyds Banking rolled out Voice Identification to its Halifax, Lloyds Bank and Bank of Scotland customers in October 2018, offering customers the chance to enroll for voice authentication. It’s now the most commonly used mode of authentication among the bank’s customer base. Deutsche Telekom introduced its “SprachID” in August 2018 and has also experienced high degrees of adoption. Active Voice Biometrics solutions, like LumenVox’, offer a convenient and secure way to enable this functionality for businesses and consumers.
  4. Active voice biometrics for self-service applications for end-consumers is still very compelling – For self-service channels, active voice biometrics offer a convenient, and secure means to authenticate customers who need to perform tasks such as password resets, updating of personal details, secure app interactions and pre-authentication in an IVR queue and, as such, remains a compelling offering. The LumenVox Password Reset solution allows users to actively authenticate by repeating a random set of words or a passphrase. Once they’re authenticated they can reset their passwords immediately. Users can also use the same voiceprint to authenticate across multiple channels – like mobile and web – for a convenient omnichannel experience.
  5. Cloud-based hybrid voice biometric systems are becoming a trend – Especially for non-financial sector call centers. Globally, more and more organizations are looking for solutions that are flexible and operate on a pay-as-you-use basis. A voice biometric solution is no different. A consolidated voice bank that can streamline customer engagement and leverage the customer’s voice across multiple brands and commercial entities, like LumenVox’s Call Center solution, offers organizations a compelling solution.

Ready to learn more about the top five voice biometric authentication trends and how the LumenVox suite of solutions can aid your organization in obtaining maximum fraud prevention while offering customers exceptional experiences? Contact us today!

Windows Pre-Login Password Reset Application unlocks accounts and resets passwords from a locked home screen

Windows Pre-Login Password Reset Application unlocks accounts and resets passwords from a locked home screen

Whether we like it or not, and even with the recent announcement from Microsoft, it will be a long time before passwords are eradicated. However, with the release of LumenVox Authentication Suite 7.1, and the availability of the Windows Pre-Login Password Reset Application, the issue of forgotten passwords and account lockouts will no longer drain resources and productivity for organizations with employees running Windows 7, 8.x and 10.

Aimed at driving down helpdesk costs and empowering employees to quickly self-service, the automated LumenVox Windows Pre-Login Password Reset Application is based on the Windows Credential provider framework and plugs seamlessly into the existing login screen, displaying as an additional user title. With the user interface (UI) language determined by the user’s current windows system settings, from the locked screen, the user can easily follow the prompts to begin the reset or unlock process via three different authentication methods using previously enrolled models:

  1. Voice Callback to a Registered Phone Number:  Selecting the voice option triggers an out of band voice biometric authentication process in which a phone call from the LumenVox engine to the user’s registered phone number is placed. The call and onscreen workflow are synced so the user hears and sees on screen prompts from their locked screen.
  1. Knowledge Based Authentication (KBA) Within the Login Screen:  Selecting the KBA option triggers a pop-up window on the locked screen displaying a question and answer form. Multiple questions must be answered correctly to authenticate.
  2. One Time Password Sent to a Registered Mobile Phone via Text Message (SMS):  Not requiring explicit enrollment, upon selection of the out of band SMS option, a 6-digit one-time password is sent to the user’s registered mobile phone as a text message. The one-time password must then be entered in the pop-up window on the locked screen.

Once the user has successfully authenticated, a temporary password is generated automatically, allowing them to reset or unlock their account in a matter of minutes, 24/7.

Worried that remote employees won’t have access to the solution? The LumenVox Windows Pre-Login Password Reset Application functions outside of a company’s network by using VPN capabilities from the Windows login screen.

To learn more, download our product information sheet and/or contact us today.

Announcing LumenVox Authentication Suite 7.1

Announcing LumenVox Authentication Suite 7.1

LumenVox is excited to announce the release of LumenVox Authentication Suite 7.1. With this latest version, LumenVox is further broadening our suite of solutions to provide organizations with additional multifactor authentication deployment and fraud prevention options.

“The updates and expansion of products demonstrate LumenVox’ commitment to providing speech, authentication, and fraud prevention solutions on a global scale that are both flexible and cost-effective, for the improvement of Call Center CX and ROI,” stated LumenVox CEO, Edward Miller.

LumenVox Authentication Suite 7.1 features include:

  • Availability of the LumenVox Fraud Scanner. Designed to enable fraud teams to more actively track and report ongoing fraudulent activity, the LumenVox Fraud Scanner utilizes advanced voice biometric algorithms coupled with state-of-the-art neural networks to alert teams with a prioritized list of suspicious calls.
  • A mobile application (iOS and Android) deployment option for the LumenVox Password Reset Solution. With the simple scan of a QR code, a user can configure the generic reset application with their organization’s desired configurations and branding, enabling multifactor authentication for account unlocking or password resetting, directly from the user’s mobile device, 24/7.
  • LumenVox Pre-Login Password Reset application for Windows. Based on the Windows Credential provider framework, the LumenVox Pre-Login Password Reset application plugs seamlessly into the user’s existing login screen, allowing users to select their preferred method of authentication (voice biometric, SMS, KBA) to unlock or reset their password, even if they are not currently logged in.
  • Updates made to language packs for multifactor authentication utilizing active voice biometric authentication and knowledge-based authentication (KBA). Active voice biometric languages updated: English, German, Spanish, Portuguese, Dutch, Czech, and Polish. KBA languages updated: Arabic, German, British English, American English, Spanish, French, Italian, Japanese, Portuguese, Russian, Simplified Chinese.

For more detailed information about each of the highlighted features from LumenVox Authentication Suite 7.1, stay tuned, and be sure to follow us on Twitter, Facebook, or LinkedIn.