VoiceDNA is a modern product for biometric voice authentication, also used for voice analysis and audio customer service, offered by the Vietnamese startup Namitech, also known as Nami Technology.
Ho Chi Minh City-based Namitech argues that VoiceDNA is more than twice as fast as Nuance biometrics, both in terms of registration and identity verification. The software can be implemented for text-dependent and text-independent verification, and has an efficiency of detecting presentation attacks of up to 95%. The startup has just raised $2 million for its further development.
Comparable to “Voice DNA” is the proprietary solution from BiometrIQ – VoiceToken, which provides strong, two-step voice authentication with a very high effectiveness of almost 99%, also in the case of attacks based on speech synthesis. It only takes a dozen or so seconds to verify your identity.
An interesting case of using voice biometrics in medicine. Voice biometrics restores the patient’s ability to generate speech. After a stroke, a patient (Ania) who has completely lost her speech can speak in her own voice, using a biometric avatar controlled by her mind.
This is made possible by a special implant, implanted outside the brain, that uses voice and facial biometrics to derive speech data and inferences based on cerebral assessment. An artificial intelligence algorithm trained on a recording of the patient’s wedding speech, the main one of her new voice. Cerebral interrogation when the patient talks or acts.
Ania’s avatar is animated on a graphical grid using emotion signals expressing happiness, sadness and surprise.
The creators of the implant are scientists from the University of California in San Francisco and Berkeley.
How much should a car know about its driver? Qualcomm announced a collaboration with SoundHound to develop and test SoundHound Chat AI for automotive. The first available voice assistant with generative AI capabilities will be added to the Snapdragon Digital Chassis concept vehicle. For example, the voice assistant will be able to find a recipe, add the necessary ingredients to a digital shopping cart and have them ready for pickup at the driver’s local grocery store at a specific time.
While AI service providers believe megaplatforms increase convenience and will change the way people live, privacy researchers call them “data-guzzling machines” that have the unparalleled power to see, listen and collect information about what they are doing and where they are driving. This is according to research by organizations responsible for privacy protection regarding the collection and use of data by automotive brands.
Game developers strive to improve player experience by designing immersive environments. A key element of this immersion is the integration of seamless payment methods that allow players to purchase in-game items, upgrade their characters or access premium content without interrupting the flow of the game.
Fingerprint scanners and facial recognition systems are already common and provide a safe and convenient alternative to traditional systems and the use of passwords and PIN codes. Thanks to this, game fans can continuously enjoy the game thanks to biometric authentication at any stage. However, the use of behavioral biometrics in the gaming industry will allow us to go a step further – recognizing people will be possible based on their unique behaviors. These could be typing patterns or mouse movements. This means that the user’s natural interaction with the game interface will create a unique behavioral signature that can be used to authenticate the user in subsequent game sessions.
Daon’s newly patented set of ALX algorithms for voice, face and document verification has hit the market. This technology is intended to improve the detection of voice fraud, mainly supported by artificial intelligence.
BiometrIQ, also as part of one of its research projects, is working on a package of solutions to increase the security of biometric systems and protect against attacks based on voice theft. Thanks to the original solution, it will be possible to determine the authenticity of the voice source with a probability of up to 99%.
Voice authentication, called logging in with your voice, is not as common as we would like. Why is this happening and what challenges await voice biometrics?
1. Data safety.
This is the basic factor that determines whether or not to use a given solution. After all, each of us wants to feel safe and be convinced that by using a given service/solution, we will not lose data and will not fall victim to fraud, in this case based on voice theft. The security guarantee is the most important factor for the development and dissemination of voice biometrics. So what are the benefits of using voice biometrics? There is nothing better than using a multi-factor authentication method. Nearly 80% of Polish people already use it or use biometric data*). Multi-factor authentication is almost 100% secure, combining different, independent authentication methods. It follows that, apart from the password, a second authentication element was born, for example, the biometric means – the voice. Such solutions protect us more strongly against hacker attacks than simple solutions only help with a pin or password. From the point of view of the network of criminals, it is precisely biometric security that many security measures can be circumvented, all thanks to the high performance of biometric systems. You can read more about multi-factor authentication and how the #VoiceToken application works on this method on our blog https://biometriq.pl/en/multi-factor-authentication-voice-strong-protection-against-hackers/
2. User privacy protection
Loss of privacy is one of the biggest fears of people when using voice as an authentication method. Research shows that 1/3 of Polish people are afraid of information leakage (in general)*). The most common questions are where and how the data will be stored, whether it will be properly secured and whether it will not be used unlawfully. Protecting information about ourselves becomes a priority. Please note that by sharing your biometric data, in this case your voice, you must give your consent. without such consent of the voice sample, the so-called voice prints may not be used for this or any other purpose. Otherwise, it may have serious consequences. Recently, lawsuits for violation of the privacy of biometric data have been filed against 2 major companies on the global market: Meta and the Albertsons food chain. In both cases, it is about the collection and storage of voice samples without consent, in the case of discount – employees, and in the case of the owner of Facebook – Instagram subscribers. For the breach of privacy, the two companies agreed to pay damages of $1.1 million and $68.5 million, respectively. These cases clearly show that there is no consent to violate this sphere of life and any such actions will be clearly punished. High penalties for abuses are also intended to serve as a warning and prevent further violations in this area. More about these cases here
3. Trust in technology (social acceptance)
The dissemination of technology is a component of the aforementioned factors such as security or privacy protection, but to a large extent its acceptance and popularity can also be influenced by “customer experience” factors such as ease of use, comfort of use, speed of the entire process. The pace at which we live today makes people value time more and more. The sooner we can get things done, the better. Therefore, forms of remote service are increasingly preferred, without the need to visit banks, offices or shops. “Talking” as a form of authorization or authentication is here to come about faster than we think, meeting all these criteria. Due to the fact that fast innovative technology reaches young users, it is very likely that this group will be the largest recipient of voice technologies in some time. This is confirmed by research*), according to which 70% of people aged 25-35 already use double authentication or use biometric data, while the use of voice authentication methods is effective only in 50% of the population.
4. The prospect of savings vs costs
Cost plays an important role in the implementation of any solution, and if it is too high, it can be an obstacle to implementation. It is no different in the case of voice biometrics. Nevertheless, in financial institutions, it is worth considering this matter in the category of savings resulting from the implementation of biometric systems. Banks will benefit from the lack of the need to issue cards to customers and the reduction of the circulation of paper documents. and no need to purchase and maintain token-type devices or other authentication terminals. The use of the voice form of authentication does not require the installation of additional devices. In addition, institutions can also generate savings related to the maintenance of office premises, because in this case a visit to the office is not required. Reducing office space or moving partially to virtual service can generate significant profits.
*) source: Cyberthreats, What Poles are afraid of, report, June 2022 https://krd.pl/centrum-prasowe/raporty/2022/cyberzagrozenia-czego-boja-sie-polacy
Actions in accordance with the idea of sustainable development*) are becoming a priority today. Protecting the planet and its resources for future generations takes on new value. Already today, it is not just a kind of whim, but specific business activities through which the business is perceived, the company’s competitiveness is built, and thus, in a sense, the brand. Awareness of the impact of business activity on the environment, economic order and society, the use of improvements and safe technologies become a priority for the future of companies and a better life. So it is also for us.
When creating its own solutions in the field of voice biometrics, BiometrIQ, apart from functionality and accessibility, definitely takes into account the impact on the environment, in particular reducing the carbon footprint**). He believes that even the smallest action can have a real impact on protecting our planet.
Thanks to the implementation of our voice biometrics system, which allows you to confirm the identity of the interlocutor during a voice call, it is possible to resign from a personal visit to the bank, which translates into a reduction of the carbon footprint. With one transaction, almost 15 times.
Detailed calculations can be found below.
=> 1 transaction with personal visits to a bank/office:
return trip 10 km by bus (value determined by determining the average distance between the place of residence and the bank/office for 297 people interviewed), carbon footprint for a mini class car 108g CO2/km (https://www.gov.uk/government/publications/greenhouse-gas-reporting-conversion-factors-2019)
Carbon footprint attributed to a person per transaction with in-person visits in a mini car trip = 1080 g CO2 per transaction
=> 1 remote transaction settling matters in a bank/office:
1 mobile phone transaction: duration 10 minutes (conversation duration based on 517 phone calls), IP transmission, bit rate 256 kb/s, which gives = 150 MB/transaction
Data transmission carbon footprint (based on IEEE Comm. Magazine) 0.5 kg CO2/GB
Carbon footprint of 1 mobile phone transaction: 500 g CO2/GB * 0.15 GB = 75 g CO2 per transaction.
Introduced next year (2024), in accordance with European law (Corporate Sustainability Reporting Directive, CSRD), the obligation to publish non-financial information in the field of ESG shows how important this issue is for the functioning of business in the context of the entire environment in which we find ourselves, i.e. our partners, suppliers, customers, society.
It should also be emphasized that the European Union with the goal of achieving climate neutrality as a community in 2050 and its package for reducing CO2 emissions by 55 percent. in 2030, it is the most ambitious in the world in its commitment.
*Sustainable development “assumes intergenerational solidarity, which means that the current generations should take into account the needs of future generations when meeting their needs. This idea is not only about reducing the negative impact on the environment and economy, but also about driving positive processes that will bring benefits to all inhabitants of the planet.
** Carbon footprint is the total sum of greenhouse gas emissions caused directly or indirectly by a given person, organization, event or product. It is a kind of ecological footprint. The carbon footprint includes emissions of carbon dioxide, methane, nitrous oxide and other greenhouse gases expressed in CO₂ equivalent.
źródła: Wikipedia, artykuł “Koncepcja zrównoważonego rozwoju…”, K. Augustyniak-Woźnica
- Don’t recklessly leave voice samples on the internet. Take control of what you post.
You can already create voice replicas based on several-second recordings. The fewer recordings left in the public domain, the less likely it is that a voice pattern will be created to be used for dishonest purposes. Conscious voice management reduces the risk of theft.
- Have limited trust in voice assistants and people whose voice sounds suspicious.
In case you are not sure whether the person on the other end of the handset is who they claim to be, hang up and contact this person again to confirm the compatibility.
- Use strong multi-factor authentication (2-3 factor authentication) when logging in.
This type of multi-factor authentication, in particular based on voice biometrics (e.g. VoiceToken), is 100% safe and effective. What it is and how it works you can read at the link.
- On personal devices (computer, laptop, smartphone) use professional voice biometric systems.
In this way, you will avoid extortion or loss of image by a potential fraudster impersonating another person for dishonest purposes.
- Use available systems for evaluating the viability (or veracity) of a voice stream source.
Personal data is any information that enables the identification of a specific person. e.g. name and surname, PESEL number, address, date of birth, but also biometric data such as face or voice. Pursuant to the Act of May 10, 2018, each of these data is protected. Personal data protection is a set of laws and regulations designed to protect the privacy* of individuals. The rights concern the methods of processing, creating and collecting personal data, including by companies and service providers. In the era of the development of digital services and artificial intelligence, the protection of privacy, in particular biometric data, takes on a whole new meaning.
The voice is the source of information. Why is it worth protecting?
Voice in biometrics is a source of knowledge about a person. On the basis of the voice, i.e. a unique biometric feature, it is possible not only to identify, but also, according to many studies, thanks to advanced algorithms to determine age, gender, social status and even emotional state or determine the diseases that a given person suffers from. When subjected to effective analysis, it can be used to create even complete profiles of people. Biometric features play a huge role in identifying identity, simplifying everyday functioning in various areas of life, but when they fall into the wrong hands, they can be used in a dishonest way and reveal knowledge that we would not like. Therefore, it is extremely important that biometric data is rationally used and protected. The regulations governing the protection of personal data require constant updating due to rapidly changing market conditions, digital technological advances and the increasing use of biometrics.
Voice samples and security. Real threats
In order to use the voice biometric services, it is necessary to provide your unique VoicePrint, i.e. a voice pattern created on the basis of a voice sample. VoicePrint is an encrypted code consisting of behavioral and physical characteristics, used to verify the identity of the person for whom it was created. Voice samples recorded for the purpose of creating VoicePrint should be collected only with the consent of the person concerned and processed for the purpose for which they were collected, in accordance with the applicable GDPR. Usually, this is additionally regulated by the contract concluded with the client by the service provider (a company or institution providing voice-based services). Importantly, voice samples are used only to create VoicePrints – after creating them, they are immediately deleted. VoicePrints are stored in databases while we are customers. When resigning from the VoicePrint service, they should also be removed from the database. The contract and the method of data storage should guarantee full security of biometric data, similarly to traditional data.
It is worth remembering that voice samples left knowingly or not in the public domain may be tempting to process them and obtain sensitive information. Processing voice recordings (synthesis or conversion) to steal voice is a common practice used by hackers. Progressive research works provide more and more new algorithms to counteract such situations. One of the latest works carried out by BiomterIQ is innovative protections of voice streams, which may soon effectively eliminate voice theft based on recordings.
Is there a place for ethical activities in biometrics?
Ethical issues are a very important point to consider in the context of protecting the privacy of biometric data, including voice.
According to experts from the EP Think Tank (a draft regulation on artificial intelligence), the main problem is the registration of voice samples itself, which involves the creation of a unique biometric template that identifies a given person. Experts believe that “creating biometric templates means converting unique physical features into digital data, which leads to the creation of more and more data and reliance on algorithms. Due to the fact that the features that uniquely identify a person are related to the description of their body parts, their collection and use violates personal autonomy and human dignity. What’s more, anyone who in the future comes into possession of templates has the ability to track a person anywhere in the world and for any purpose. Man cannot protect himself from this because he cannot change his identifiers.”
And what is your opinion?
Undoubtedly, it seems necessary to create a separate “code” regulating the collection, processing and use of biometric data, while preserving the right to privacy in the broadest aspect of this meaning. The implementation of voice biometrics on a large scale will depend on this – says Director of BiometrIQ Andrzej Tymecki.
*Privacy (from Latin privatus ‘personal, pertaining to a person, ordinary, not pertaining to the state’) – the right of an individual to live their own life, arranged according to their will, with all external interference limited to a minimum.
Voice biometrics technologies are already so developed that literally a dozen or so seconds of speech are enough for the system to recognize whether the person who wants to authenticate is who he claims to be. More and more perfect biometric systems, including voice recognition and synthesis, begin to gain in value every year in the context of their common applications. More and more research is being conducted on the development of biometric technologies. The forecasted biometrics market, according to “Biometric System Market in the Global Forecast to 2022 report”, last year reached USD 32.5 billion and we can expect its further growth. The premise for this is, for example, the latest agenda of the US Government, which encourages investment in modern solutions of identity verification based on biometrics. The main reason is the security and availability that these solutions can offer.
It is not without reason that biometric solutions, mainly based on a fingerprint, face or iris scanning, were the first to be used in financial institutions to confirm identity. We are talking about logging in to the mobile application or the recently introduced authorization of payments using fingerprints (biometric card implemented by Bank Pocztowy). Some banks, in accordance with the latest trends, are becoming more and more interested in voice biometrics. Trust in voice authentication is growing. The research shows that 50% of the society is convinced of this form of authorization. There are tests and first implementations (Bank Zachodni WBK, present Santander). Voice biometrics convinces with a high level of security and the possibility of using it in remote channels, without access to the office. It is these two factors that may determine the use of voice biometrics for payment authorization in the near future. This is confirmed by experts from EY, who claim that the universality of voice payments will depend on the readiness of technology and measures ensuring 100% security and privacy.
Is voice biometrics reserved only for banks? Well, nothing could be more wrong. More and more institutions and companies from the trade, health, property protection and even media sectors will decide to implement voice biometric systems. Being modern, using the latest trends and available technologies based on neural networks is not only a privilege but a necessity in building a competitive offer, gaining and retaining customers. The spread of remote channels and new forms of online service, such as v-commerce (voice shopping), are additional factors driving the development of voice biometrics. Guarantee of security of this type of solutions, availability and at the same time naturalness of use and convenience mean that investments in services based on voice biometrics can only pay off.
Orange and T-Mobile telecoms know this, as they were the first in Poland to implement voice technology on hotlines, focusing on comfort and significantly reducing service costs. The voice authentication of the orange operator is used by tens of thousands of individual customers. The Turkish operator Turkcell can also boast of implementation on a larger scale, reaching several million users.
Emirates with the advent of the pandemic at Dubai Airport introduced smart, contactless airport experience based on facial and iris recognition technology. This is how Emirates passengers can check in before their flight, complete immigration formalities, access the lounge and board the aircraft. Biometric boarding based on facial recognition has also been used by Brazilian carriers GOL and LATAM for almost a year at 3 airports in Sao Paulo, Rio de Janeiro and Santos Dumont. The implementation of voice biometrics in this area seems to be only a matter of time.
Airports are one of the places that, due to the service of a huge number of passengers, will strive to automate the service process and implement more and more modern ways of fast, safe and convenient service for passengers – the combination of face or iris scanning technology with the unique feature of the voice can significantly improve the passenger experience. Voice as a non-contact form of authorization has a chance to work best here.
Voice biometrics can also come to quite unusual industries, such as the hotel industry or gastronomy. Due to the growing labor costs of economy hotels in connection with the reduction of the human factor as well as the growing trend of spontaneous travel, remote forms of self-service (self-check-in technologies) will become more and more popular. It is therefore possible that in a few or a dozen or so years, the guest will check in using a smartphone and open the hotel door with her voice.
Advanced voice biometrics systems are also an excellent “weapon” to fight online abuses based on voice, effectively preventing its theft. The emerging algorithms are already able to distinguish an artificial voice from a real one with almost 100% certainty.
In fact, it can be said that voice biometrics will eventually appear in every aspect of our lives. because speech is the most natural mechanism of communication between people. It is estimated that the global voice biometrics market will increase even 3 times by 2024.
sources: newseria.pl, ryneklotniczy.pl, spiderweb.pl, infowire.pl, own studies