Voice biometrics, a truly reliable process ?
In the perpetual quest for renewal of the UX (user experience), the voice appears from year to year as inevitable. Successor to touch and facial recognition, its multiple applications, beyond interaction, include the identification of individuals. According to Rita Singh, a Carnegie Mellon researcher specializing in machine learning applied to voice, “It has been known for centuries that the voice carries a wealth of information. Artificial intelligence can be used to extract that information.
Identifying oneself through our voice was until then something reserved for science fiction, yet we are closer to it than it seems! However, like the various controversies linked to new technologies, is it a reliable and secure process?
What is voice biometrics actually?
“Le son de votre voix est en train de devenir un nouveau type d’empreinte digitale.”
Voice biometrics is a scientific and technological field that aims to develop applications to verify a person’s identity solely through his or her voice.
The voice is in fact governed by prosody, the set of vocal characteristics (timbre, pitch, valence etc…) specific to each human being. Forming a true vocal imprint, these characteristics are identified in order to make them correspond to a reference model, thus serving for identification.
Technically, machine learning is very popular in this field of research because it allows a system to improve by itself. It is important to specify this because the reliability of the technology will depend in part on the rate of accuracy it will offer. According to the principle of “Machine Learning”; each time information is entered (i.e., a user will speak) the system will take advantage of this data in order to function on the one hand, and to refine its results on the other.
Can we really rely on it?
Often imagined and used for authentication, voice biometrics is in the midst of questions about its reliability and security. The risks of fraud also apply to the field of voice, because stealing a code and stealing a voice are both technically feasible.
Recently integrated and experimented by banking players, voice biometrics remains a “touchy” subject because behind its attractive functionality, there are nevertheless significant risks of loopholes. It should be noted that in the field of security, the ingenuity of the people imagining the systems is equivalent to that of those seeking to rout them.
However, several things must be taken into account! First of all, a voice contains a hundred or so specific characteristics which, depending on the quality of the audio capture and information processing, make this medium a robust means of identification. On the other hand, as we said before, machine learning models are adapted to this kind of practice because they refine their accuracy as they occur. Thus, today we have intelligent systems with an enormous amount of information, which are proving to be increasingly infallible.
The answer as to reliability is therefore mixed: on the one hand, like any mode of identification, flaws exist and will exist, but on the other hand, voice is positioning itself as robust enough to deserve its chance.
What can we expect from it?
In our opinion, and in the opinion of many experts, voice biometrics, for the time being, should be used in addition to other more proven authentication methods. In doing so, the respective advantages of the different methods can become complementary. For example, combining voice and facial identification is already an avenue being explored by many players.
In any case, one thing is certain: voice interaction is a part of all our uses. We’ve talked a lot about biometrics in the authentication sense because it is the most inherent subject in the technology, and above all the one that raises questions. However, biometrics is not just for that! One example, which you can already use at home if you have a smart speaker, is Voice Match, the ability of assistants to recognize individuals from the same family. From this comes the advanced personalization of the experience, in terms of preferences, accessibility or authorizations for example.
If you would like to learn more about voice biometrics, we recommend that you ask our experts at voice-market.io to answer your questions about our partners’ solutions.