A few days ago, we launched a new version of the voice coherence demo, in which you can check whose voice among famous Polish athletes is closest to yours. Our list includes the names of such Olympians as Iga Świątek, Michał Kwiatkowski, Anita Włodarczyk and Hubert Hurkacz. In total, we selected as many as 20 people from 13 different disciplines.
How does the demo work?
To check who your voice is similar to, just visit the website https://demo.biometriq.pl:8443/ and read the text we have prepared, the reading time of which is only 30 seconds. During this time, we record a voice sample, which is simultaneously compared with the voices of selected 20 athletes. The results are displayed immediately in a column in the form of % convergence.
The result may show:
=> significant % convergence with only one person
=> show no convergence, then the table will remain unchanged and 0 will be shown everywhere
=> convergence with several people (this happens most often).
Remember that voices may be confusingly similar to each other, but not biometrically consistent. Conversely, they may be biometrically consistent but not audibly similar. This is because the human ear primarily perceives the intensity and tone of sound along with the location of its source, and biometric systems extract from the audio stream and analyze several features that make the analyzed voice unique.
What does biometric integrity testing give us and when is it helpful?
The algorithm used in this exercise may be used commercially in the future in systems for verifying the identity of people and detecting voice-based fraud, the so-called deepfakes. This model is constantly being developed and improved by us to be as effective and reliable as possible, which is associated with obtaining a probability of assessing the speaker’s truthfulness of over 90%.