SIIP – Speaker Identification Integrated Project
Funded by the European Commission, SIIP research project will develop a break-through Suspect Identification solution based on a novel Speaker Identification (SID) engine and Global Info Sharing Mechanism (GISM) which 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 (including social-media).
SIIP advanced Speaker Identification engine will fuse multiple speech analytic algorithms such as: Voiceprints recognition, Gender-ID, Age detection, Language& Accent ID, Keyword & Taxonomy Spotting and Voice cloning detection. This fusion will result in highly reliable and confident detection, keeping the False-Positives & False-Negatives to the minimum and improving the judicial admissibility of the Speaker Identification Technology.
|Title of the project|
Speaker Identification Integrated Project
|Total Grant||10,530,000 €|
|Project initiator and coordinator||Gideon Hazzani, Verint|
SIIP will enable LEAs to overcome two main challenges they face today:
- The adoption of multiple fake and arbitrary identities by terrorists and criminals using telecommunication and Internet mediums in aim to avoid their lawful interception and tracking by LEAS, through prepaid cell-phones, Frequent alerting of SIM cards in cell-phones , Random access to other people’s phones and Using different nick names in various Internet VOIP applications such as: Tango, ooVoo, Skype, Viber and G-Talk, etc.
- “The second side problem” - The difficulty to identify unknown participants in a lawfully intercepted call of a known suspect.
Depending on adequate oversight provided by a system of judicial warrant and in accordance with the legal and ethical frameworks, the SIIP solution will have the following capabilities and strengths:
- Run on any speech source and channel (Internet, Social-Media, PSTN, Cellular and SATCOM) and provide LEAs with better intelligence and improved judicial admissible evidence of lawful intercepted calls.
- Associate each speaker identification with rich-metadata (Identifiers used by the suspect, Personal details, Location-profiles, Social-connections and many more), taken from variety of sources including the WEB and Social-Media.
- Enrolment of rich suspect voice and metadata from Telecom and Internet sources, incl. Social-Media (e.g. YouTube).
- In accordance with INTERPOL regulations establish global-secured info sharing mechanism (for voiceprints and their associated metadata) between LEAs around the world, via INTERPOL, expediting the investigation process and saving significant LEA resources.
SIIP will integrate ethical, legal and societal research especially in relation to the use of speech recognition for evidential purposes in trials (e.g. providing guidelines for lawful interception and ensuring that there is a low false-positive rate). SIIP will explore the possibility to use performing and efficient Voice recognition biometric technologies for secuirty purposes while preserving individuals' privacy. Moreover, its integrated solution will endorse the privacy by design principles and safeguards will be included at different levels of the system to prevent misuse as well as security incidents.
Finally, SIIP will analyze the societal impact of SIIP solution to ensure that the research done meets the needs of the society, show the substantial benefits of such a solution for the society and ensure that the research won’t have negative impacts on the society when implemented and when deployed.
SIIP will be designed, developed and tested by a consortium of 18 partners, bringing together LEAs (INTERPOL and police forces from the UK and Portugal), SMEs, industrial hi-tech companies and academic institutes from a variety of fields including Security, Speech analytics, Social Media Analytics and more.