For many years, law enforcement agencies, lawyers, and judges have used voice forensic authentication to recognize suspects .
The identification of a person through speech samples with a forensic quality is challenging.
The fact that I could program something that actually does “something” in the real world was fascinating.
When the time to go to a university came about, I was also dabbling in some other specializations, but automatization won in the end.
Finally, our research would not get shelved and gather dust as the academic and commercial spheres would become connected.
Thus, my idea was one of synergy, friendship, research and helping the “good guys”.
In general, speaker recognition, like other bioinformatics features, is used to discriminate people through their voice.
Automatic speaker recognition can be classified into two tasks: speaker verification and identification.
That was probably the biggest impulse and a true eye-opener.
There was nobody in the Czech republic dealing with top-level language and speaker recognition, even the working style was different, and we had to progress in our research much faster – basically on a daily basis.