A new international effort to identify terrorists and other criminals by their voices has passed its first test, according to a report in Joseph Farah’s G2 Bulletin.
Officials with the international police agency INTERPOL said the Speaker Identification Integrated Project successfully was used in a field test in Lisbon, Portugal.
“Based on a fictional scenario involving an international investigation between the Italian Carabinieri and the Portuguese Polícia Judiciária, the SiiP system successfully identified unknown speakers from a research database using key identifiers such as gender, age, language and accent,” the organization reported.
“More than 130 speaker identification researchers and experts, forensic experts and police investigators from some 40 law enforcement agencies from around the world took part in the field test.”
The four-year project costing more than $10 million was funded by the European Commission and utilizes a Speaker Identification engine and a Global Info Sharing Mechanism. That combination will “identify unknown speakers that are captured in lawfully intercepted calls, in recorded crime or terror arenas and in any other type of speech medium and channel.”
That includes social media.
It combines technology that uses voiceprint recognition, gender-ID and age detection, language and accent ID, keyword and taxonomy spotting and more.
“This fusion will result in highly reliable and confident detection, keeping the false positives and false-negatives to the minimum and improving the judicial admissibility of the Speaker Identification Technology.”
The project’s website explains that the work will be of assistance to law enforcement in several ways.