In its final field test held on 22nd November, in Lyon (France), the Speaker Identification Integrated Project (SIIP) successfully demonstrated the system’s innovative capabilities as language independent speaker identification system for spotting persons under suspicion from the authorities.
Using a database with real audio recordings, the UK’s Metropolitan Police Service and the Portuguese Polícia Judiciária, demonstrated how unknown speakers talking in different languages could be identified through social media or lawfully intercepted audios using a fusion of key markers such as gender, age, language and accent.
Some 110 speaker identification researchers and experts, forensic experts, intelligence analysts and police investigators from more than 50 countries participated in the event that took place in the facilities of INTERPOL.
INOV is involved in several phases of the SIIP project, from the definition of requirements of final users, the system, and of use cases, to the proof of concept and integration. INOV also supported the stage of system validation and testing and was responsible for the development of a Telecommunications Simulator for Call Interception installed in the facilities of the Carabinieri (Italy) and the Polícia Judiciária (Portugal).
The four-year EU-funded research project (May 2014 – April 2018) is run by an international consortium of 19 partners who developed this cutting-edge speaker identification technology to help law enforcement agencies identify individuals under suspicion.
SIIP has received funding from the European Union’s FP7 framework under grant agreement No 607784.