Blog

Santa Vs CPaaS - Getting your online orders delivered

With over a third of shoppers planning to do Christmas shopping solely online, and 61% taking a hybrid approach, how can you ensure your company's orders are delivered, on time and securely? Find out how you can improve Christmas shopping for your customers by using CPaaS.

It’s that time of the year again, sales are up, staff are busy and black friday is (thankfully) in the past. But with over a third of shoppers planning to do Christmas shopping solely online, and 61% taking a hybrid approach , how can you ensure your company's orders are delivered, on time and securely?

Spirits (and cases) are high

Here we are again. The holidays are around the corner and COVID cases are on the rise. Many savvy customers have taken to online shopping to keep themselves, and others, safe during the pandemic. Retailers have received, packed and processed orders, and sent them for shipping. They now have the responsibility to make sure their customers receive the order. The last thing left is to make sure the package gets to the right place, at the right time and is safely received by the customer.

Signed, sealed and…delivered?

Over 5 million parcels were lost or stolen in the past year in the UK, which equates to roughly 10 parcels a minute that don’t get to customers. This problem is even more severe in the US, with up to 1.7 million packages going missing every day. Why is this?

• Lack of Communication and Notifications
  Citizens Advice said that as many as 20 million people – 38% of all UK adults – had received a “Sorry you were out” card in the last year, despite being home at the time. This issue could be solved simply, with better communication and notifications ensuring customers know when their parcel is due to arrive, and that delivery drivers know when to knock or where to leave the parcel safely if the customer can’t be at home.
• Overworked delivery drivers
  With some delivery drivers in the US expected to deliver up to 300 parcels a day, giving less than 2 minutes per parcel, it's no surprise that mistakes are made. This is no fault of the drivers, unrealistic expectations and a lack of communication options make this system unreliable. Imagine if the customer had the ability to message the driver as they were near to inform them “I am home, please knock” or “I am not home but I have left the porch unlocked, please leave there”. Good news is, you can.
• No penalties for poor service
  Currently only Royal mail faces fines for poor service, however UK charity Citizens Advice Bureau believes that UK regulator OFCOM should have the power to broaden these sanctions to all delivery services. This would give new focus to improving the customer experience, and luckily there are easily implemented systems that would deliver an exceptional experience, whilst keeping overheads low.

It's no surprise that parcels go missing, with massive strain on the system and exponential growth in online orders. However this doesn’t change the fact that missing parcels, that are no fault of the retailers, result in a negative customer service experience and a bad reputation for the retailer. So how can you take more control over your online orders, ensuring your customers receive their orders and the great customer experience that they deserve?

We wish you a Merry CPaaS

CPaaS stands for Communications Platform as a Service. It is a cloud-based communication solution which allows businesses to add multiple customisable features without the need for on-premise hardware or large capital investment. Here are 5 ways in which CPaaS can be the elf-like powerhouse behind your company's deliveries ensuring they are on-par with Santa-level customer experience.

Communications are for life, not just for Christmas

Of course, problems with deliveries are not just a seasonal issue. The pandemic has drastically altered how people shop, now and forever more.

Looking to improve your customer’s experience through every step of the buying process, giving you more control over your service reputation and future proofing your online delivery model? Sign up with Aculab Cloud free today at
https://cloud.aculab.com/login/enrol

SMS Scams over the Holidays: Ready, Set, GO.

In the last year, global e-commerce has jumped to over $26.7 trillion, accelerated by COVID-19 according to United Nations UN News. It all sounds like great news for the economy, however fraudsters are following this upward trend and adapting their scams.

What is SMS Phishing?

SMS Phishing (also known as Smishing) is the act of committing text message fraud to try to lure victims into revealing account information or installing malware. Similar to Phishing, cybercriminals use SMS Phishing in an attempt to steal credit card details or other sensitive information, by disguising as a trustworthy organization. SMS Phishing has grown in popularity with cybercriminals now that smartphones are widely used, as it enables them to steal sensitive financial and personal information without having to break through the security defenses of a computer or network while also attracting considerably higher open rates than email. According to MobileMarketer.com, while email recipients only open about 20% of their messages, SMS recipients open 98% of their texts.

“On a small screen and with a limited ability to vet links and attachments before clicking on them, consumers and business users are exposed to more phishing risks than ever before,” says IDC’s Phil Hochmuth.

Examples of SMS Phishing

• Fake shipping notifications: Many delivery scams start with a text message about delivering a package to your address, according to the Better Business Bureau. These messages often include a “tracking link” that you are urged to click in order to update your delivery or payment preferences.
• Phony bank account balance warnings: A link to a website prompting for a bank account number or PIN of a debit card.
• Fake text from the IRS or Power company: Saying you owe unpaid taxes and that the IRS will arrest you if you don’t pay now via a link.
• Fake Prize notifications: Requesting personal information to deliver the reward.
• Bogus Covid-19 contact tracing messages: Requesting Personal information.

Combating the threat of fraudsters

Companies are aggressively looking for ways, including authentication and fraud detection solutions, to simultaneously streamline authentication and strengthen security. A “State of Intelligent Authentication and Fraud Prevention 2021” survey conducted by Opus Research revealed that “customer authentication [across all channels] has a direct impact on fraud detection and fraud prevention,” with a rare 100% of respondents agreeing or strongly agreeing with the statement.

While PINs/Passwords are still the most common factor in use, respondents also incorporate other factors including out-of-band delivery of one-time-passwords, knowledge-based authentication via security questions and voice biometrics.

How to Protect yourself: Tips for Identifying Scammers

1. Do your research to double check the details. If you get an unexpected sms text from a delivery company, or bank, look up the bank, agency or organization and get in touch directly, without using any contact information in the SMS text.
2. Claim a prize: No legitimate lottery, sweepstakes, or business will ask you to pay to claim a prize or ask for your bank details to deposit your “cash prize”.
3. Beware of urgent texts: “Attention. Fraudulent activity has been detected on your account. Act Now.” Scammers often create a sense of urgency to bypass your better instincts. Take your time and ask questions to avoid being rushed into a bad situation.
4. Refund owing to you from a retailer: Notifications involving money owed “Our records show that you overpaid for (a product or service). Kindly supply your bank routing and account number to receive your refund.” Again, don’t click on the link, check with the source.
5. Never verify passwords via a text: Any text that attempts to verify your Apple ID / Amazon account / Bank account is suspicious.

What can you do if you receive these messages:

• Report spam texts to the FCC and your carrier—Report as junk or spam. You can also contact your cell phone carrier to report as spam and file a report with the Federal Trade Commission at ftc.gov/complaint.
• Stay alert—Don’t click on any links, as they can install malware on your device, which collects your personal information.
• Ignore spam text—Directly replying to a spam text message lets a spammer know that your number is genuine. What happens next? They can sell your phone number to other spammers who might bombard you with promises of free gifts and product offers.

Finally, keep in mind fraudsters are continuously evolving and adapting their strategies, so most of all, be aware and be safe, especially this holiday shopping season.

STIR/SHAKEN and Robocalls

The STIR/SHAKEN framework has been the talk of the North American telecoms town over the past few years, but what is it, how does it impact your business, and how can you make sure your business’s communications conform to this framework?

STIR/SHAKEN stands for Secure Telephone Identity Revisited/Signature-based Handling of Asserted information using toKENs – you can see why an acronym was needed! It’s up and running in the USA, and will soon be live in Canada. Other countries are also considering its adoption.

This latest podcast breaks this down further, looking at how this mechanism enables the person receiving the call to judge the validity of the caller ID.

7 Reasons to implement Cloud based Voice Biometric today

What is Voice Biometric Authentication?

From privacy and security, to ease of use and savings. Discover how your business can benefit from cloud based voice biometrics.

Voice Biometrics characterises a person's voice for use in Speaker Verification - an application of AI-based voice technology that uses a voice imprint to authenticate or confirm an individual’s identity. Various vocal features and attributes such as pronunciation, pitch, tone, dialect, and style of speech all contribute to our vocal identity and allow verification / authentication for users. This process is extremely fast (think tens of milliseconds), needing only a couple of seconds of speech to store the voiceprint. That is why it is already used in many systems and services that have become an integral part of our daily routines, such as Google Voice, Amazon Alexa, and other virtual assistants.

Here are 7 reasons why your organisation should implement cloud-based Voice Biometrics technology today.

1. Fighting Fraud

Voice biometric systems operate on hundreds or even thousands of features of the human voice, making verification highly accurate, and a powerful tool in fighting fraud. Adding voice biometric technology not only reduces the risk of fraud by identifying the customer unambiguously, but also protects victims of fraud and impersonations, the customers themselves. Call centers today, with the help of voice biometrics, are already building real-time databases of “blacklisted voiceprints” as a security measure.

2. Security

The traditional verification methods like password or PIN can be easily tracked or hacked, while the voice of an individual can be as distinctive and unique as the fingerprints captured by many computer systems. That’s why Voice Biometrics are being implemented in large scale applications such as remote banking, government e-services and healthcare. Groundbreaking advances in Artificial Intelligence (AI) and the science of Big Data, give Voice Biometrics the ability to identify a speaker, rapidly and reliably. Voice Biometric APIs, such as VoiSentry’s, enable developers to add enhanced security and convenience of biometric voice authentication to their customer contact applications.

3. Privacy & Engagement

Voice Biometrics keeps the privacy of users intact, and the end-users engaged.

With other authentication methods, simple PINs or passwords are usually supplemented with personal information such as mother’s maiden name, date of birth, or a pet’s name. But many end-users are reluctant to share such information with more than a few services – they quite rightly believe that doing so makes their accounts far more vulnerable to attack, because once one such service has been breached, an attacker will have easy access to all the other services.

What’s more, some of this information can be inconvenient to use – it can be forgotten, or sometimes expressed or spelled out in different ways (different capitalisation, optional punctuation marks, etc.) – causing confusion and delays in accessing services or systems.

Whatever the reason, simple knowledge-based authentication makes for an experience that is tedious and uncomfortable for users. The key is to find methods of authentication and verification that are effective, accurate, and easy for customer engagement. Voice Biometrics is often the only feasible method to achieve all these aims simultaneously.

4. Operational Cost Savings

Several use cases for voice biometric authentication show immense operational cost savings including Contact and Call Centers that are traditionally agent-assisted. With voice biometrics, the customer is identified, authenticated and routed to the appropriate call flow via IVR for processing their request, without any human interaction. Voice Biometrics reduces the average authentication time by up to 80%, which also frees up the agents, meaning they can be more engaged in focusing on other complex issues without compromising the customer experience.

5. Ease of Use

Voice Biometrics is a win-win for users. Rather than customers memorizing their passwords or keeping them saved in their notebooks and phones, a voice biometric system can verify their identity with only a short sample of their voice – whether taken from a natural conversation or in a more controlled fashion.

In many situations, a Voice Biometric solution is the only technology that can provide reliable authentication with such ease – there is no need for a keyboard, a web-cam, or any special hardware such as a fingerprint reader, and there is virtually no overhead in terms of overall transaction time.

What’s more, the most powerful Voice Biometric systems are language-independent, recognizing unique voice characteristics regardless of language or accent. This is especially important in regions where multiple languages or dialects are spoken.

Voice Biometrics can provide a smooth user experience that still accurately verifies the identity of customers.

6. Foster accessibility

Voice biometrics solutions are suitable for almost everyone, including many of those with speech-related disabilities. “A good language-independent Voice Biometric system relies on the voice characteristics rather than the actual words spoken.” Wheeler (a digital analyst at Aculab, who has cerebral palsy and limited speech) explained. “This means it can still be used by people with impaired speech.”

Voice Biometrics provider, Aculab Cloud, has recently published a blog post illustrating the accessibility features of its VoiSentry Speaker Verification & Identification (SVI) system.

7. Get started Quickly

Voice Biometrics can be implemented easily on your platform of choice – hardware server, data center, cloud, or even a SaaS pay-as-you-go model. Best of all, it is highly scalable and can be applied in a variety of different applications such as contact centers, healthcare management, public services and financial systems.

These flexible integration options make it simple to implement cloud-based Voice Biometric solutions. Aculab VoiSentry with SaaS, cloud-based and / or subscription-based models, enables developers to add the enhanced security and user convenience of biometric voice authentication to their customer contact applications within hours.

MORE RESOURCES

Want to learn more about how Aculab VoiSentry’s Voice Biometrics can help facilitate a seamless, secure and password-less user experience? Click here to try the Demo.

STIR / SHAKEN in CPaaS

Robocalls: Good guy vs Bad guy

Tired of robocalls? Who isn't. I barely answer my cell phone unless it's from someone I know. With the usage of cell phones in the US rising substantially over the past decade, consumers have seen a sharp rise in the number of spoof and robocalls they receive.

46% of Americans receive spam every day, that’s 46 billion robocalls in 2020 alone.

• 175,699,527 per working day
• 122,014 per minute
• 2,034 per second

Ouch! Add to that, robocall scams make headlines almost daily. Just Google “robocall scam” and you’ll get pages and pages of results. But what about the good-guy robocalls? Wait, good-guy robocalls? Yes! There are LOTS of occasions in which businesses and organizations might conduct good, or even emergency robocalls, such as:

Local emergency alerts: A gas leak in a neighborhood, water contamination, or when extreme weather is headed into a community, such as those needing immediate evacuation notifications due to the recent California fires.

Affordable housing / apartment management notifications: In today's world, tenants expect more. With so many ways to get in touch with tenants, large scale apartment complexes from luxury to affordable housing are offering several options to get the best results out of the landlord-tenant relationships. Sending out mass text, and/or voice messages, combined with email, makes it easier than ever for property management teams to more effectively reach their residents.

Health alerts: The ongoing health crisis requires the fast dissemination of information. Additionally, the healthcare industry also relies on robocalls for medical appointment and care reminders (ie. taking meds, wellness check-ins and post op).

That’s a pretty sizable amount of calls that are legitimate. Unfortunately, spoofing and bad-guy robocalls are Crushing Reputable Businesses.

Spoofing is when a caller deliberately falsified the information transmitted to your Caller ID display to disguise their identity. Scammers often use neighbor spoofing so it appears that an incoming call is coming from a local number, or they spoof a number from a company or a government agency that you may already know and trust.

Congress passed the TRACED Act on December 30, 2019, with its primary goal to combat the rising number of malicious and illegal phone calls and text messages in the US. STIR (Secure Telephony Identity Revisited) and SHAKEN (Secure Handling of Asserted Information using toKENs) is a framework that aims to regain and strengthen consumer trust in the communications industry by combatting Caller ID spoofing, helping protect consumers from falling victim to malicious activity, fraud and abuse.

Without getting too technical, STIR/SHAKEN uses digital certificates, based on common public key cryptography techniques, to attest whether the calling phone number, the Caller ID, is genuine. Each phone service provider obtains their own digital certificate from a trusted authority, and the certificate technology enables the recipient to decide whether the Caller ID is legitimate and has not been spoofed.

Now, what about the good-guy robocalls? Well, unfortunately for businesses legitimately communicating with their customers, plain voice-only robocalls may not be enough. The solution may be a reputable CPaaS (Communication Platform as a Service). A CPaaS is a cloud-based delivery model that focuses on enhancing communication channels by allowing organizations and businesses to add various features to their existing applications. The CPaaS market is forecast to grow from $4.2 billion in 2019 to $17.7 billion in 2024.

Added capabilities, like voice calls and SMS, can be deployed through easy-to-use communication APIs (Application Program Interfaces), presenting highly-attested, legitimate Caller IDs, thus making it easy for the recipients to identify the calling business, and elicit a response.

Now, reputable CPaaS providers are committed to the fight against bad-guy robocalls, and have taken steps to raise the bar for high quality, good-guy robocalls (e.g. appointment reminders, emergency notifications) by implementing STIR/SHAKEN Caller ID full attestation. Time will tell whether STIR/SHAKEN has helped with spoofing and unwanted robocalls.

However, some CPaaS providers have further upped the ante by implementing AI-AMD (AI-driven Answering Machine Detection). This, with over 99% accuracy (compare the 94-95% industry norm), translates to a big reduction in silent calls, one cause of which is AMD misclassifying a human answering as a machine, meaning that good, useful robocalls may be construed as bad-guy robocalls by those picking up the phone.

Keep in mind that STIR/ SHAKEN applies to phone calls only. However, work is ongoing in the communications industry to reduce bad-guy SMS usage, for example The Campaign Registry for 10 digit long code (10DLC) messaging.

While bad-guy robocalls continue to be a problem, what can you do?

If you’re a business or organization which places automated calls to inform your customers:

• Choose a CPaaS which has implemented STIR/SHAKEN;
• Ideally use a Caller ID purchased through that CPaaS, resulting in the highest level of attestation for that number;
• Ensure that calls placed to that number are answered, with a brief explanation to the caller of what the service does;
• Choose a CPaaS with very accurate AMD, resulting in fewer silent calls.

If you’re on the receiving end of unwanted or bad-guy robocalls:

About Aculab

Aculab is a global provider of advanced speech and signal processing technologies for use in telecommunication applications. The company offers deployment-proven options for many automated communications-related systems. Its wide range of platforms serves the evolving needs of systems integrators, whether for on-premise, data centre hosted, or cloud-based solution delivery.

Aculab offers development APIs for voice, advanced speech, fax, data, and SMS, on hardware, software and cloud-based platforms, giving users the choice between capital investment and cost-effective, ‘pay as you go’ alternatives.

How To: Add voice and video calls to your webpage

The advent of the internet fundamentally changed how people communicate. We are now able to connect with people across the globe almost instantaneously, not only through voice and text, but also through video communication.

In this blog post we will be diving into WebRTC, showing how it can help you as a business, and explaining what you can achieve with Aculab Cloud WebRTC.

What is WebRTC?

WebRTC stands for Web Real Time Communication, and allows people to transfer media (voice and video) and data between browsers and mobile devices. A common API is provided across a wide set of supported browsers and devices and, with media support built in, WebRTC browser calls can be supported without the need to download software or plugins. This all goes to make WebRTC a particularly well-supported, easy-to-use method of communication.

Examples

Some notable examples of the utilisation of WebRTC are Discord, Facebook Messenger and Google Meet/Google Hangouts. All of these applications have the ability to transfer voice and video between people via their browsers, easily and reliably. And, if using from the browser, nothing needs to be downloaded or installed.

History

WebRTC was introduced in 2011 by Google as an open source project after acquiring GIPS (Global IP Solutions) in 2010. Steadily since then, usage has been growing, but a major turning point was the Covid-19 pandemic, when people were forced to isolate and in-person interaction was much restricted. Due to its sudden increase in popularity, WebRTC was standardised in 2021, having become a staple of modern communication.

Security

WebRTC security consists of three mandatory WebRTC encryption specifications: Secure Real Time Protocol (SRTP), secure encryption key exchange, and secure signaling. These features combined ensure the media and data being transferred are encrypted and safe from being tampered with.

But this isn’t the only reason why WebRTC is more secure than other video and voice calling: As mentioned previously, you don’t need to download any software or install any apps or plugins to use calls in the browser. When you download or install software, you are allowing it to run on your device, which could lead to hacking if that software isn’t well protected. An example of this was seen recently when major security issues were discovered by users of Zoom when hackers could easily input code into a user’s computer, known as ‘Remote Code Execution’. In contrast, WebRTC uses well-proven software within the browser.

Users are also notified before a website utilises their webcam or microphone to capture video/audio. This is typically in the form of a pop-up before the microphone or webcam is turned on and, while the webcam is operating, a small light next to it.

Using Aculab Cloud WebRTC for your business

You may be wondering: Why should I be using WebRTC? Well, it's built in to the browser, and widely supported across different browsers – and it's likely the user already has a browser, so they don't need a phone as well. WebRTC allows video as well as voice communication, all captured and displayed using their device's mic, camera, speaker and screen. WebRTC is secure, and you can use it from the browser without having to download or install anything. WebRTC means the call can be part of a much richer dialog – for example, a Doctor may have their patient's records searchable and displayed, all in the same browser tab as the video call to the patient. Finally, WebRTC isn’t just for laptops and computers, it’s also available on mobile devices like smartphones and tablets.

At the low level, Aculab Cloud WebRTC allows you to:

• Make voice and video calls between browsers;
• Place calls to Aculab Cloud inbound voice services, including connecting to conventional outbound phone calls;
• Answer calls from Aculab Cloud voice services, including from conventional inbound phone calls.

At the high level, this allows use cases such as:

• A doctor calls their patient from the browser, with the patient records searchable and displayed in the same tab right next to the call. The call could be voice to their phone number, or voice and video to their browser.
• A receptionist receives calls on their browser, with the appointments-booking system shown in the same tab. The call could be voice from a conventional phone call, or voice and video from the caller’s browser.
• A receptionist receives calls on their browser, with the appointments-booking system shown in the same tab. The call could be voice from a conventional phone call, or voice and video from the caller’s browser.

If you'd like to try a demo of calling an Aculab Cloud inbound voice service from your browser, click https://www.aculab.com/cloud/demos-all/webrtc/.

If you'd like to try us out, please sign up to Aculab Cloud, https://cloud.aculab.com/login/enrol.

Aculab Cloud pricing is dependent upon your usage, so you only pay for what you use – there are no flat fees. As well as this, you receive other great features like Amazon Polly Text-To-Speech, Google Speech Recognition and our own, best in class, AI-driven Answering Machine Detection and Voice Biometrics.

If you have any questions regarding WebRTC or anything covered in this post, please don’t hesitate to speak to one of our experts at This email address is being protected from spambots. You need JavaScript enabled to view it..

To try our WebRTC demo, follow https://www.aculab.com/cloud/demos-all/webrtc/

or to enrol free with Aculab Cloud, follow https://cloud.aculab.com/login/enrol .

How to: Reduce contact centre verification time by 80%

Verification of identity has changed a lot over the years. As the world has shifted away from face-to-face interactions to phone and digital solutions, so has the way in which we identify and verify who we are.

This has led to a problem – securely verifying a person’s identity takes time, and as we all know, time is money.

According to Microsoft’s 2019 survey on global customer service, 31% of customers cite having to repeat or provide their data multiple times as the most frustrating aspect of poor customer service.

This is often due to problems with automatic speech recognition (ASR) based systems, which are notoriously bad at recognising proper names. This means not only annoyance for end-users but also a need for call centre agent’s time in order to deal with issues arising from this, such as error recovery and rectifying customer satisfaction.

Security can’t be compromised for speed

As the use of high-level authentication is usually reserved for services such as financial companies, it is imperative that no corners can be cut in the hope of speeding up the process. In fact, with cybercrime spiking hugely throughout the pandemic, businesses need a solution that is MORE secure than traditional methods, while accelerating the process and creating a streamlined end-user customer experience.

Customer Experience

We all lead busy lives, the last thing your end user wants is spending time wracking their brain to remember the make of their first car or what password is needed from their 100+ accounts.

Customers call contact centres wanting solutions. Voice biometrics allows contact centres to deliver these quickly and securely, removing barriers instead of creating them.

How does Aculab’s Voice Biometrics work?

Instead of requiring a password (KBA) or a token-based solution, Aculab’s voice biometrics engine (VoiSentry) uses a hybrid approach to analyse a voice sample as a means of highly accurate and secure authentication. This hybrid approach consists of:

• General phonemic, phonological and para-linguistic features as well as a number of unpublished proprietary analysis methods designed specifically for speaker recognition
• A combination of AI and further proprietary algorithms to combine the information from the various biometrics into a single result.

This highly-optimised combination of biometrics markers provides a much more accurate and reliable result than that of identification using just one or two markers.

These markers are compiled using AI algorithms to form a customer’s unique voiceprint. This process is very simple from an end-user’s perspective, with the user having to repeat a short phrase 3 times. Unlike other similar products, VoiSentry allows each user to create their own unique pass-phrase. This enhances security even further as any attacker would need to copy both the target voice and the spoken words to access. Once this voiceprint has been created it is held securely within the VoiSentry engine.

The next time the customer calls, it is as simple as comparing their voice on the call to their voiceprint to securely confirm their identity.

Not convinced? Try Aculab’s free demo to see if you can try fool the system. We wager you won’t.

How to implement these services?

As highlighted, traditional methods of ID&V are costly, inefficient, and place barriers between customers and their queries.

Voice Biometrics is truly the future. In a world where personal data is becoming less and less secure, there is one option that is virtually impossible to fake, hack or duplicate when combined with personal knowledge – our voice.

To find out more, visit https://www.aculab.com/voice-biometrics/ or get in touch to implement voice biometrics into your contact centre solution.

Reminder: The world is reopening

Appointment reminders are critical to many industries around the world, now more than ever. From the crucial services to the downright fun, in the new world emerging from lockdown, we all need a little certainty in our lives.

CPaaS (Communications Platform as a Service) has been somewhat of an unsung hero during the pandemic, working behind the scenes to aid with delivering our food, keeping in contact with our loved ones and broadcasting pivotal healthcare messaging. However, its use is far from over. As we all start to surface from our social hibernation, many industries that have clung on through the past year are now facing new problems that CPaaS can be an integral tool in helping to solve.

Reopening Anxiety

A recent survey undertaken by Anxiety UK showed while 37% of respondents are looking forward to returning to normal life, nearly an equal percentage (36%) are worried about post lockdown life. Of those who were feeling anxious about the lifting of restrictions, nearly half cited the pressures of socialising generally as their biggest concern.

"Any type of life change is associated with stress and anxiety," said Marney White, a clinical psychologist at the Yale School of Public Health. "Even if the change is exciting."

As a large part of anxiety stems from the unknown, appointment reminders/ confirmations can be a huge help in combating the worries of venturing out into public settings. With CPaaS, your customers could book a haircut or a table at a restaurant weeks in advance and receive timely reminders in the days or even hours before the booking, with the ability to reply to the service to confirm their attendance. Speaking from experience, this control over the situation is a great tool in helping to take the first steps in approaching anxiety-inducing situations.

Hospitality

Hospitality, one of the largest sectors in the UK with 10% of total employment, has been hard-hit by COVID-19. As many businesses in this sector are allowed to reopen, they are now facing a new issue. Namely, the number of no-shows for reservations. 

What’s ISO 27001 and why should your company implement it?

As the risks associated with cyberattacks and data breaches continue to increase, information security has become a critical issue for every organisation. An effective approach should help defend against both external attacks and common internal threats such as accidental breaches and human error.

ISO 27001 is the international standard that provides the specification for an information security management system (ISMS). This is a systematic approach consisting of people, processes and technology that helps you protect and manage all your organisations information through risk management.

ISO 27001 focuses on protecting three key aspects of information:

• Confidentiality – The information is not available or disclosed to unauthorised people, entities, or processes.
• Integrity – The information is complete and accurate, and protected from corruption.
• Availability – The information is accessible and usable as and when authorised users require it.

ISO 27001 is one of the most popular information security standards in the world. The standard has been designed to help organisations manage their security practices consistently and cost-effectively. It is technology and vendor neutral and is applicable to all organisations irrespective of their size, type, or nature.

ISO 27001 is the mainstay of the ISO 27000 series; a family of mutually supporting information security standards that together provide a globally recognised framework for best practice information security management. These standards help organisations keep their information assets secure by offering a set of specifications, codes of conduct and best practice guidelines to ensure strong information security management.

ISO 27001 Clauses

The main part of the ISO 27001 consists of 11 clauses (0 to 10) which are mandatory. Clauses 0 to 3 set the introduction of the ISO 27001 standard (introduction, scope, normative references, terms and conditions). The following clauses 4 to 10 include: context of the organisation, leadership, planning, support, operation, performance evaluation and continual improvement.

ISO 27001 Controls

The second part of the ISO 27001 standard, called Annex A, provides a guideline for 114 controls, covering the breadth of information security management including areas such as physical access control, firewall policies, security staff awareness programmes, procedures for monitoring threats, incident management processes and encryption.

What are the benefits of ISO 27001?

• ISO 27001 will help you secure your information in all its forms – An ISMS helps protect all forms of information whether digital, paper-based or stored in the cloud.
• Increase your attack resilience – Implementing and maintaining an ISMS will significantly increase your organisation’s resilience to cyber-attacks.
• Protect what matters – Whether the scope of your ISMS covers your entire organisation or just the parts that deal with information, ISO 27001 protects against technology-based risks and other more common threats such as poorly informed staff or ineffective procedures.
• Respond to the evolving security threat landscape – An ISMS constantly adapts to changes both in the threat environment and inside the organisation, ensuring that information security risks are effectively managed over time.
• Protect the quality of your data – An ISMS provides the controls for best practice; the policies and procedures must be written by the company. It also consists of technical and physical controls to protect the confidentiality, availability, and integrity of your information.
• Embed information security into your company culture – The standards holistic approach covers the entire organisation, not just the IT department so employees can readily understand risks and embrace security controls as part of their everyday working practices.

How to get ISO 27001 Certified

Once an organisation has met the various requirements stipulated by ISO 27001, the next step is to seek certification. Certification is the procedure by which an external certification body provides written assurance that an organisations ISMS conforms to the requirements of ISO 27001. Due to the certification of ISO 27001 not being mandatory, not all organisations choose to achieve it, however, there are many benefits to certification. As well as helping you protect your information, and comply with relevant legislation, ISO 27001 certification holds a distinct market value by providing clear externally validated proof of your organisations willingness to meet internationally accepted information security standards.

Aculab ensures the upmost importance on information security, and ensures that any customer data that the company stores or processes, are held to the highest standards, and these standards are consistently applied and updated. Aculab has been certified by BSI (British Standards Institute), an accredited company, for complying with the ISO 27001:2013 standard. This follows the successful implementation of their Information Security Management System (ISMS).

This can be viewed on: https://www.aculab.com/why-aculab/standards

A Voice Biometrics system that works with non-verbal speakers

What are the difficulties when accessing services over the telephone or online?

As a non-verbal communicator, I’ve had a whole host of poor experiences with companies where I can’t service an account through my channel of choice since my Cerebral Palsy limits my ability to speak, as well as my manual dexterity.

One particularly poor experience was with a bank who ‘improved’ its service by moving from a traditional Interactive Voice Response (IVR) where you had to select ‘1’ to find out your balance, to a system that relied on speech recognition. This caused an unintentional barrier and could exclude customers from using telephone banking or cause them to compromise their security details by using text to speech services to retain easy access to essential services.

It is especially difficult to navigate menu or conversation based IVR dialogues if you have a disability that impacts your dexterity, as well as your speech.

What are the security issues surrounding current authentication solutions?

As hackers and identity thieves have become more and more sophisticated, knowledge-based authentication using password or PIN security just isn’t effective at keeping customer information safe and secure. To combat the latest security threats, businesses and other services need to update their security perimeters.

This is important for businesses, especially those who the customer has trusted to run their bank account and manage their finances. In the UK, the financial regulatory body, the Financial Conduct Authority or FCA, completed a survey (Financial Lives 2020) that showed that 1 in 5 UK adults, equating to over 10 million people, had given their credit or debit card to someone else to use, or had shared their current account, savings account or credit card PIN or password with another person in the last 12 months, with customers with some characteristics of vulnerability more likely to be a victim of financial abuse.

This makes sense as customers who may have difficulty remembering passwords may have to rely on someone else, just to do simple things like access their bank account.

As it stands, with some services I have to enlist the help of a trusted relative to communicate and verify who I am. This is concerning as it could potentially lead to fraudsters gaining access to my details and hacking into my account by misrepresenting me.

How can a language independent Voice Biometrics system help?

We’ve all been there, you need to call a service supplier and tell them about a problem or ask a question about your service and you are faced with a barrage of questions like, ‘Enter your date of birth’; ‘the numeric digits of your postcode’, or a personal favourite, ‘the 4th and 8th digits of your security PIN’ (how many times have you forgotten that!). With 87% of adults in the UK using a smartphone, it is safe to assume a lot of these calls will be made using such a device and sometimes, just getting back to a keypad can lead a customer to miss the prompt and have to start again. This can be frustrating for a customer who just wants to get some information. Now imagine changing that process so you only have to answer a simple question or prompt.

Voice biometrics overcomes traditional security risks, helping customers stay in control, reducing the risk of passwords and PIN numbers being shared and helping financial service companies protect their customers' information. The technology is equipped to handle both physical and behavioural features within people’s speech patterns, making it virtually fraud-proof. A good language independent Voice Biometric system relies on the voice characteristics rather than the actual words spoken. This means it can still be used by people with impaired speech as long as they can vocalise to some extent.

For a customer, enabling a voice response makes the authentication process smooth as they would be expecting to speak when they made the call. By focusing on voice biometrics rather than spoken word recognition, authentication can be more accessible, enabling people with speech disorders to use these services without compromising their security details. It also gets over all the hurdles of the customer forgetting their PIN number as the system is identifying the customer's voice. Giving customers easy access and reducing errors can result in a big improvement for the customer experience and reduces agent handling time making contact centres more efficient.

A system that really works for non-verbal communicators!

Since starting with Aculab one of the products that has impressed me the most is VoiSentry, which uses voice biometrics to enable speaker verification and authentication to an organisation’s applications. VoiSentry uses artificial intelligence and speech patterns to distinguish individuals. This can transform how a call centre operates and can help financial services organisations reduce fraud.

At Aculab, developers have created the VoiSentry system, which extracts many diverse vocal traits and uses a hybrid approach, intertwining artificial neural networks, signal processing technology and analytic linguistics, to create frictionless authentication.

I tested the VoiSentry demo to see if the software works for someone who is affected by cerebral palsy and has limited speech and paralysis in their left side. Honestly, I was impressed to find that the application was able to identify and verify me every single time. I made numerous attempts, making different noises to challenge the software. In the end, it demonstrated that it was able to pick up the nuances of my voice in order to get a verification. I’ve not had an experience like that with any of my current service providers which shows how cutting edge VoiSentry is, whilst being incredibly simple for an end user.

By integrating VoiSentry, both businesses and customers alike get numerous benefits, such as enhanced security and reduced identity and verification time. In addition to this, VoiSentry meets compliance obligations for data protection whilst being likely to feel less invasive than other forms of authentication. It is also a cost-effective option, meaning that companies can replace time-consuming manual processes and improve their returns on investments each year. By using this technology, the identification process is more transparent for both caller and call taker, resulting in improved agent morale with more time to engage with callers.

Reece Wheeler

How Aculab is helping me Kickstart my career

Starting a new job can be one of the most stressful situations we encounter as adults.

When you throw starting your very first job after leaving education into the mix, whilst in the middle of a pandemic, it is a hard call over whether the interview process or the first day was the most nerve-wracking.

I thought I would write about my experience to help others starting on a similar path.

Before starting this role, I had an exceptionally long seven months of job searching, which was an experience. Having never experienced recruitment agencies and the trials of social media recruitment processes, I hadn’t really known what to expect. Unfortunately, like a lot of graduates I found myself in a position where my qualifications didn't really fit the job I would aspire to do as a career. I found myself lacking in experience for my ideal role and in a bit of a catch 22 of needing experience, but not being able to get a role to get the experience.

That was when I first heard of the Kickstart Scheme. It was a perfect opportunity for someone like me, a graduate without much work experience, looking for an opportunity to really start my career. The Digital Analyst opportunity from Aculab immediately attracted me, as I’m very interested in technology and communications. The offering made clear that there were lots of training opportunities and I felt like it would be a role where I could build practical skills, making this opportunity perfect for me.

In my job search I’ve used every application and interview as an opportunity to gain experience, but I’ve found some processes really tough. I’m non-verbal and use a device to communicate (another reason why a tech-savvy communication firm appealed to me), so you can imagine some of the difficulties I had when interviewing remotely! Unfortunately, some firms just weren’t prepared to interview me if I couldn’t speak on a zoom call.

At the interview, I was so nervous. I had prepared by researching Aculab and the services offered and drafting answers for questions I thought might come up. Just to say, from my perspective it was refreshing for an organisation to easily adapt the process for my disability and give me time to type my responses. Despite my challenges and nerves, I felt really comfortable having a discussion about the role and that is one of my standout first impressions.

Aculab are really open and wanted to understand how I communicate best so they can adapt to me, which has meant that I’ve been able to settle in and make good connections with the rest of the induction group.

So far, I’ve just completed my first two weeks and I feel like I’ve learnt so much already. In this time I've already picked up an overview of the business, been able to start learning programming languages like Python and gotten to grips with Praat and analysing audio files. Aculab has really met my expectations and their induction is a good mix of practical experience and self-led learning.

One of the biggest surprises has been the flexibility. As an induction group we’ve been asked about our interests and invited to do certain tasks based on our individual preferences, which is one of the things that has led to this blog. It’s definitely a lot to take in but on a six-month contract, I don’t want to waste a minute of it and it feels like the whole induction group I’m in are all eager to get stuck in.

My experience so far has been brilliant, and I’m so pleased I took the Kickstart opportunity with Aculab. It is a bit surreal to be an employee at an organisation for the first time, whilst not actually leaving my house and it’s been a real learning curve, but everyone I’ve met at Aculab has been supportive and welcoming. One thing’s for sure, I cannot wait to carry on with my development over the next six months to improve my knowledge and skills.

Reece Wheeler

Why a Local Cloud is the right choice for secure cloud communications

Maybe it’s time to rethink your view of what Cloud architecture means. Cloud use is cost effective, provides huge operational benefits, AND is able to be utilised in a secure way.

As someone who has followed the rise of cloud computing for a decade, it is apparent to me that there are still regional differences in opinion of the safety of cloud infrastructures. The US has a lead over Europe, for example, in cloud adoption (Gartner), and that is likely down to a multitude of factors:

• The tech vendors in the US have heavily promoted the use of their cloud-based products
• Many of the tech giants providing the underlying infrastructure are US companies
• The tech buyer community is more open to try new ideas in the US
• The regulations governing data security and privacy are less onerous in the US
• The US is such a large market that many of the business transactions take place solely in the US; less scope for cross-border activities

Considering each point in turn helps to understand the current situation and provides guidance on the route forwards to remove any concerns and drive European cloud adoption forwards.

Vendor push

The majority of players in the enterprise telecommunications space are US companies, and in their drive to maintain market share and profitability, they have all adopted cloud-based approaches for at least part of their portfolio. In turn, the market for enterprise communications software and services in the US is the largest globally, and they have an appetite for new technologies such as cloud that will improve their bottom line.
In addition, most of the SaaS service offerings that are hosted on public clouds use either Amazon AWS, Google Cloud, Microsoft Azure or IBM Cloud - all of which, as evidenced by Statista, are US corporates who rolled out their platforms in the US first and then the rest of the world.

Openness to new ideas

The tech buyer community is more open to try new ideas in the US. In my opinion, based partly on three years spent earlier in my career living over there, there is a real openness to trying new ideas in the US, compared to a more conservative approach throughout Europe. This tends to lead to the majority of early adopters being in the US region.

Regulatory differences

The regulations governing data security and privacy are less onerous in the US. In addition, the US is such a large market that many of the business transactions take place solely in the US; less scope for cross-border activities.
If you consider the US versus Europe in terms of markets and market regulations, there is certainly more of a single market in the US with Europe being more fragmented, and with varying degrees of concern for data sovereignty; this leads to economies of scale for rollouts to meet a common set of regulations.

Is there a better way?

Yes – in short, what we at Aculab have termed ‘Local Cloud’.

It’s still a cloud infrastructure (not on-premise) thus giving you all the benefits of a cloud solution such as flexibility, scalability and cost efficiency; but you are able to control certain aspects such as locality of the data that is stored on or passed through the system. It’s a cloud that covers one country (or region) rather than being a global cloud where you have no control of where your data is stored or processed.

Data you put on one Cloud stays in that Cloud, we don't copy it around unless you ask us to.

This type of infrastructure is better in many ways for customers

1. Peace of mind regarding data security
2. Ability to maintain and adhere to strict regulations for data privacy such as the GDPR (EU) or PIPEDA (Canada)
3. Ability for cloud suppliers to tailor an architecture to a specific region, not cost effective on a global scale
4. Use of a single cloud from one vendor rather than a solution build from multiple vendors means there is less complexity with regard to data privacy – to meet the GDPR, for example, there is only one data processor to consider

Aculab's Local Cloud approach

Aculab Cloud is a communications platform as a service (CPaaS). It is hosted on Amazon AWS (an Infrastructure-as-a-Service platform), and using Aculab Cloud our clients build their own end-user facing software-as-a-service (SaaS) offerings to provide, for example bulk voice call or messaging services to/from their client base.

For Aculab, what Local Cloud means is basically that we replicate our whole cloud infrastructure in multiple locations, with each one being a distinct standalone system able to operate in isolation of the other regions. 

Our current regions:

• 0-2-0 Europe (Dublin, Ireland)
• 1-2-0 US-East
• 2-2-0 US-West

However, due to the way we have created our architecture, we can spin up new clouds in specific country or region in a very short timescale. We are continually evaluating our regions on offer – under consideration at present are:

• Canada
• Australia
• Germany

If you have a need for a secure cloud in a particular region, get in touch using the short form on our Local Cloud page and we can work on a proposal, or it may be that your chosen region is already in our pipeline!

Andrew Nicholson, Senior Product Manager

When will telecom gateways be extinct?

Within Aculab, we’re often discussing the general acceptance of VoIP and whether we’re any closer to the time when traditional TDM voice will disappear and ALL enterprise voice communications needs will be handled via IP connections rather than TDM E1 and T1 circuits.

One thing that is clear is that whilst we are in the midst of a large shift towards IP voice, the general use and acceptance of VoIP is still at a slower pace than we were predicting 1, 2, 5 and certainly 10 years ago. One analogy recently drawn in our discussions was with the continental drift. Plate tectonics theory states that whilst the actual speed is very slow, somewhere between the growth of a fingernail and the growth of human hair, it is relentless and unstoppable leading to the creation of new geographic features along its path, such as mountains and volcanoes – again an analogy we quite liked. Furthermore, with continental drift there is never one single source of energy or momentum, it is movement and change (or indeed growth, or 'progress') as a part of a whole.

Being right on the edge of the VoIP (or plate tectonics!) shift we’re all very aware of this movement but to the majority of people it remains an unseen level of detail that does not concern them.

But why the reluctance? Quality doesn’t get touted as the restricting factor any more. Sure, in the early days there were quality issues, and certainly calls across the public Internet wouldn’t reliably give the same quality as a dedicated PSTN line, but generally people are very happy with the compromise of that quality when taking into account the cost savings in the call. Availability doesn’t seem the reason either, most modern voice solutions use IP at its core, of both equipment and networks.

In today’s economic climate, the traditional method of moving to new technologies by ‘rip and replace’ seems to have outlived its day. For both financial and acceptability reasons, moving to new technology now means a slow, measured approach together with a well thought out solution to integrate existing legacy equipment – without losing any existing legacy functionality. Horror stories abound of where systems have been put in but then taken out due to, for example, the CEO of a company losing a particular feature which they, and perhaps only they, used across their corporate PBXs. Similarly the unavailability or poor quality of a VoIP connection when calling back into the office has forced companies to rethink their telecoms strategies.

It is sudden and rapid changes such as large earthquakes or supervolcanic events that change the global ecosystem forever, and provide the ability for scientists (or Systems Technicians) to differentiate between ineffable gradual change and see the milestones. Once these changes have happened, large scale changes take a while to happen again, so we will have to wait and see when the next big push towards VOIP happens, and the long lasting effect this has.

Gateways, however, are the crucial bridge between the old and new. They provide technological continuity in changing times. We will continue to provide this service with enterprise and telco-grade gateways to those who need them.

Aculab's range of telecommunications gateways

Turning the page in the story of cloud migration

Technology, and especially communications technology, has surely become normalised in new and interesting ways. Take the amusing and gimmicky, where a fridge can text you when your water is cold, to the more usual everyday - where you can seamlessly contact and be contacted by your local authority or social housing agency. Such a service quickly and easily allows you to complete modern life’s admin, such as paying rent, and reporting problems to landlords.

Communications Platform as a Service (CPaaS) offerings are the technological brain behind these actual processes, and can be deployed in a variety of different settings, to bolster and support a whole range of customer support and software offerings. They are only really limited in the amount of imagination used to apply them.

At the end of the day, it is still a wonder that this all happens under the surface. At the data transfer level, beneath the whirring of the fans in a server room, and the clicking of the myriad LEDs, data zips about at the speed of light, like an orchestra being conducted - greater than the sum of its parts. What’s more, the infrastructure needed to support it is deeply rooted and stable, and the service is self-regulating in that it is highly resilient, often with multiple layers of redundancy.

One of the most exciting, growing markets that Software as a Service (SaaS) Providers are building for is the social housing or housing infrastructure market. Affordable housing is high on the political agenda, and as we move through the biggest geo-political event in recent history, new technologies are being deployed to - quoting somehow both Biden and Johnson - “Build Back Better”.

Taking a much wider view, in the grand scheme of things, we are also moving from “The Internet of Things”, to “The Internet of Everything” - a world in which most processes are mediated through data transfer, where human interaction has a permeable data flow attached to it, and algorithms are deployed to manage the seamlessness of this superstructure.

It’s early days for Conversational AI integrated into everyday life, (“hello fridge, how cold is my water?”) but it’s certainly headed that way. What’s interesting is that this process can be historically tied to the migration of telecoms systems to the Cloud - which is surely a great turning point in the story of telecoms history. From buildings that house literal switchboard operators, to VOIP in data centres, data flows and the interconnections are growing ever more complex, pushing tech to become, seemingly paradoxically, both highly adaptable and specialised. On the world stage for technological systems, no more “one-size-fits-all”, no more “jack-of-all-trades”, more like the term used in the theatre world - a “triple threat”: one who can sing, dance, and act.

So, where are we now? CPaaS systems are one of the main characters in this story. And the next step for CPaaS systems - which will set some CPaaS apart from the rest - is a move from the general to the specific: whether or not they are tailored to satisfy the particular and specific needs of some markets, and by proxy, bolster the offerings that SaaS providers have to those markets. It’s like with any piece of equipment: the difference is noted in whether the tool has been designed by people who have experience using it in a variety of settings, and therefore has both the weight of experience, and the nuance of expertise behind it.

Using a reliable and intuitive CPaaS system such as Aculab Cloud means that the engine behind the telecoms is highly attuned to the market itself. And, whichever market it is that needs it, it’s important that it bolsters the supply chain process as a whole by being tailored towards the end result. In this way, the whole system works in joint orchestration. There’s no need to wrench in a piece of technology to somehow fit the process, because the tool being used is already adapted with the end-market in mind, through being inherently adaptable, moldable and plastic, having been developed by engineers who know their stuff. This is how that paradox unknots itself, and what makes for a seriously good CPaaS. So that’s the theory - but how does it work in practice?

Aculab Cloud has a whole load of features that make it highly functional and adaptable, let alone the fact that our engineers can work with you to adapt Aculab Cloud into your system architecture.
Some features are with the end-user (the tenant) in mind, some are for corporate entities such as housing organisations or landlords, and some are with SaaS providers in mind - the important thing to note is that whatever the position in the chain, the functionality of Aculab Cloud is passed along, creating a win-win for everyone. These features have been included because, at the end of the day, the social housing market needs technology that can build a sense of community, and of local governance, and this is one of the best things that a Communications Platform can do. Not reflective of some big overarching bureaucratic machine, a sense of something more devolved and at-hand. And, after all, this is people’s homes we are talking about, the technology is speaking directly to the end user’s private life. So with that, here are some features within Aculab Cloud that we think are all highly attuned towards the Social Housing market supply chain:

• Local Presentation: Numbers that end-users can see are customisable, allowing for national, local, mobile, geographically specific, and toll free Caller ID. Giving landlords the ability to have a localised/professional impression.
• Dedicated Local phone numbers: Can be set up per tenant to streamline message flow and keep messages for multiple tenants secure, whilst using a common architecture.
• Local Cloud: Because our servers are operated regionally, SaaS providers have full transparency over where their data is stored and how it is used. This is perfect for easy management of data protection (e.g. GDPR) requirements, especially when handling sensitive legal and personal information within tenancy information. Aculab is an ISO9001 and ISO27001 company, meaning we are subscribed to the highest international standards of both customer service and security within our company policy.
• Operates on “Loose-Association” channels: Phone calls and SMSs, as a medium, provide customers a way to reach out to people with whom they have only a loose association, such as housing authorities and councils. So, the end users don't need to install apps, follow Facebook pages - all the information needed to make contact is there, at hand. When you think about it, SMS and Voice operate with a high level of trust and authority, creating a positive, dynamic relationship between speaker and listener that other channels simply do not have. This allows for Voice and SMS messages to carry with them an expected level of sincerity and authority - one of the central benefits of using a CPaaS for SMS and Voice!
• Security and Privacy: Aculab Cloud is a service managed and maintained by our dedicated and experienced staff 24x7 offering a personable experience for our customers. We manage service uptime, power outages and telco carrier issues so you don’t have to.

Are facemasks a problem for Voice Biometrics?

Wearing a mask is now the primary way to limit the spread of coronavirus, and has been found to reduce the daily growth rate of reported infections in large scale populations by around 45%- but this raises a potential problem for voice biometric security.

Contents:

Wearing a mask is now the primary, everyday way to limit the spread of coronavirus, and has been reported to reduce the daily growth rate of reported infections by around 45% in large scale populations.

This raises a potential problem for voice biometric security.

People’s behaviours adapt to change and these new behaviours then become normalised. Because of this, there is now a greater demand for contactless forms of verification and identification, especially as, alongside mask wearing, contactless identification and verification becomes associated with the benefits of public health. Gloves block the success of fingerprinting; masks hinder facial recognition. This blog will attempt to find out whether mask wearing affects the ability of voice biometric identification and verification to function properly.

Voice biometrics is the next leading edge technology, facilitating high levels of security and unlocking ease of access. It allows us to use our voices to navigate our everyday interactions with the digital world around us. A voiceprint, the key, is created either through the user repeating a passphrase, or passively through conversation with customer agents. When a user wishes to access a service with a voice biometric system, all they need to do is speak, and the voice biometric AI algorithm decides whether or not the sound of their voice in that moment matches the voiceprint on file, as a key to a lock. As some examples, voice biometrics is currently used in multi-layer authentication for logging into accounts with valuable information such as online banking. It is used in healthcare to provide better diagnosis of patients, and is perhaps most widely deployed in customer facing applications such as call centres, in IVR, and for mobile applications.

Face coverings come in all sizes and thicknesses and can impact a wearer’s speech patterns, by distorting the sound of their speech or by greatly attenuating it. The masks that are most effective, which create a tighter seal around the mouth and nose, would be expected to have more of an acoustic effect on speech sounds, and therefore could possibly affect the verification process - as the natural sound of the user’s voice will have been changed.

Another possible problem comes from the fact that the way that a person speaks through a mask is also likely to change. It may be the case that users wearing masks tend to speak more clearly than without one, as they may be self-conscious of the fact that they might not be heard properly, thus changing the sound being analysed on a more fundamental level.

Overall, it's important that the convenience of Voice Biometrics should not be hampered by the user wearing a mask. The simple question therefore is: are Voice Biometric algorithms affected by the user wearing a mask, and if so, how can the algorithm adapt to take into account mask-wearing users?

To understand this problem, we’ve put Aculab’s VoiSentry algorithm to the test. A voiceprint was created without a mask. Four different styles of face covering were then worn, one after the other, and access was attempted.

#1: Filtering Facepiece (FFP3)
Heavy duty mask, very similar to the N95 mask, which is also of the PPE class FFP.

#2: Fabric Mask
This mask is made of a light, stretchy fabric. Some light fabric masks, however, are tighter, and wrap around the mouth and nose fully.

#3: Disposable Surgical Mask
One of the most commonly available masks, this is made out of a light fabric and creates as much of a seal around the mouth and nose as it can with a small strip of pliable plastic that bends to follow the contours of your face.

#4: Woolen Scarf
Not officially a mask, but a face covering. This also works as a stand-in for face-coverings and veils.

This spectrogram was taken through recording a voice, repeating the passphrase “my voice will let me in”, which is needed to create a voiceprint with VoiSentry. The audio was recorded using a phone to emulate the most common microphone type, in a small, quiet room. The audio files were then fed into an audio processing program and through a spectrogram plugin. The passphrase was repeated whilst wearing different masks, and was repeated as close as the same intonation, speed and diction as possible to the control test, with the same distance to the microphone and in the same position in the room, to maximise the potential of the only variable being the swapping in and out of face coverings.

VoiSentry enrolment and initial verification of the voiceprint occurred using a mobile phone, and with no mask. Three verification attempts were made against this initial enrolment for each face covering. Distance to microphone, diction and other variables kept the same, with some organic variability allowed.

These tests show that VoiSentry doesn't seem to be affected by the presence of masks.

Tests were also done with deliberate attempts to modulate the voice, and the way the passphrase was spoken, to test the presentation attack detection, or imposter detection. This worked well with all masks, showing that VoiSentry can still confirm a speaker's identity, even when wearing a protective mask.

What’s more, even if a genuine speaker is rejected, all that is needed is a simple update of their model to regain correct operation. Where re-enrolment is needed (which did not happen in these tests), VoiSentry provides a simple mechanism to update its voiceprints in cases such as this, to take into account mask wearing.

The efficiency and efficacy of VoiSentry lies in the fact that the algorithm has been designed to detect and verify users in noisy environments, and to take into account differences in acoustic properties, that may come from room reverberation, background noise, and distance from the microphone.

Acoustic properties may also be affected by the hardware that is picking up the signal, which may have built-in enhancements, such as gain control, dynamic equalisation, noise suppression, and other automatic signal processing. This is quite common on mobile phones.

Therefore, wearing a mask can have little to no impact on the verification and authentication process, meaning that contactless forms of verification and identification can continue to be deployed to great effect. This enables companies, products and services to gain a competitive edge in customer service situations where voice channels are available, and where the identity of the caller is critical to a business model.

Public perception of the effect of face coverings on a person's speech is somewhat exaggerated because human perception of speech is very much linked to visual perception - being able to see a speaker’s mouth move as well as discern body language, and subtle changes in facial movements all goes towards facilitating easy communication.

Fortunately for Voice Biometrics, algorithms and their performance, that is to say, matching a voiceprint to a user’s voice, operate on a highly attuned mathematical level - rather than psychological or psychoacoustic- and are designed to emulate human perception, and perhaps even improve upon it.

What is interesting is that although we can infer differences visually using a spectrogram to claim a difference in sound properties, the VoiSentry algorithm uses thousands of mathematical frames that operate over and above this dimension of our intuition. Indeed, this is the primary benefit, and some would say, magic of using an AI algorithm- it just works.