Community Research and Development Information Service - CORDIS

Periodic Report Summary 3 - SIIP (Speaker Identification Integrated Project)

Project Context and Objectives:
Fused Speaker Identification:
SIIP will develop a high performance innovative and sustainable Speaker Identification (SID) solution, running over a large voiceprint (voice sample) database (blacklist). This solution is based on integration and fusion of a series of state of the art Speech Analytic Algorithms which includes Voiceprint recognition, Gender Identification, Age identification, Language and Accent Identification, Keyword and Taxonomy spotting and voice cloning detection. This fusion will be the core technology of SIIP and will be named as ‘F-SID’ (Fused Speaker Identification) is the core technology of SIIP which will result in much higher true-positive identification of individuals, compared to each of these algorithms as stand-alone, reducing in a scale, the False-Positive/ False-Negative detection and increasing the reliability, confidence and judicial admissibility of the speaker identification.

SIIP solution adaptability:
SIIP solution will enable LEAs to run F-SID over all voice stream communication mediums that can be lawfully intercepted, by court warrant against a specific suspect, including: Internet VOIP apps (some of these applications are encrypted e.g. Skype, Tango, Viber and ooVoo are not encrypted) such as G-talk, Skype (although Skype is encrypted, LEA may use Black Box to decrypt it getting the encryption keys from the vendors and use the given keys to decrypt Skype inside the monitoring/decoder), Viber, Tango, ooVoo; PSTN; Cellular and SATCOM (satellite communication). Other voice communication mediums are “recorded” type and include social media such as YouTube or Facebook.

SIIP Solution scalability:
SIIP can be implemented at the headquarters level (where the monitoring center is placed) and at the tactical level (where the LEA investigation is done in geographical vicinity to the suspect location, by portable system that intercepts cellular channels, WiFi, xDSL or LAN), while exchanging data, in real time between these two levels (Tactical<>Headquarters).
Multisource of voiceprints enrolment (Voiceprints enrolment is done by voice sampling voice sampling): For better enrolment of suspect voiceprints, SIIP will make use of various enrolment methods:
(i) Enrolment of voiceprints at the suspect point of presence (POP) where high quality voice recording sensors and kits should be deployed (covertly) near the suspect physical presence. (ii) Enrolment of voiceprints from open source (public) social media (e.g. YouTube, Facebook) where individuals upload content which includes their voice. (iii) Enrolment of voiceprints from lawful intercepted calls from telephony/Internet peer to peer VOIP sources.

Rich metadata enrolment:
SIIP will enrol rich metadata that will be associated to the enrolled voiceprints. The rich metadata that includes for example, IP addresses, e-mail addresses, chat nick-names, social network identifiers, social network connections, cell phone identities and many more. This rich data will be enrolled from Internet open sources and from lawful intercepted telephony and Internet (VOIP) data.

International cooperation between LEAs:
The use of the “Sharing Center” would significantly improve effectiveness of international police cooperation and assists in the identification of suspects who can then be brought to justice. SIIP consists of a centralizing secured database, to be located at the ‘INTERPOL’, for analysing voice samples (retrieving and analysing voice prints for identification purposes) enhanced with rich metadata of individuals subject to request for international police cooperation.
Privacy by design concept:
SIIP integrated solution will endorse the privacy by design concept and ensure that privacy is respected at the level of each module developed and at the level of the overall system integration. Safeguards will be included at different levels of the system to prevent misuse of the SIIP solution.

Project Results:
The main results of the SIIP project during the third year of the project are as follows:

WP1 End-User & System Requirements and uses cases definition:
· The WP was extended until the end of the project
· Inputs from LEA stakeholders were received and integrated into the developed solution
· Worldwide experts pool was formed in order to ensure that the SIIP results will be aligned with the users' needs

WP2 Legal, Ethics and Societal Aspects
· WP2 activities were in full cooperation with all the relevant activities in the different WPs in order to assess the ethical, legal and societal issues.
· Resubmission of the improved version of D2.3 – according to the review comments
· Organization of discussion groups including consulting with experts and citizens
· Collecting the insights regarding speaker-identification technologies
· Engagement with experts at the PoC event in Rome
· Performing legal analysis (D2.8) in view of re-evaluation and the new developments in the field
· Submission of D2.5 – Privacy standards and data protection legislation
· Analysis of the ethical, legal and privacy issues in D4.4

WP3 – was finalised during RP2

WP4 Fusion of Lawful intercepted voice call content and metadata
· Revision of D4.1
· Submission of D4.3
· Submission of D4.4
· Completion of LI Simulator
· Interoperability and communication between WP4 components and technology
· Virtual Machines in SIIP environment - construction, enhancement, testing and installation

WP5 Biometric Voiceprint & Metadata Enrolment Sensors and Subsystems Managing Large Voiceprint Databases
· Voice print system was developed in compliance with the field's standards.

WP6 Speaker Identification Analytics
· Speech analytics engines were further developed and evaluated on different target acoustic conditions
· System fusion was developed in order to achieve improved speaker identification
· Taking an active part in the PoC and field test events (integration and evaluations)

WP7 Information Sharing Center, Identified (high score) Call Records database, Alerting system and MMI
· Finalized SISC service
· Finalized SIIP Portal V2 services and interfaces
· Release of a draft version of D7.5 - The integrated SIIP portal and Testing and validation report, Quality assurance report.

WP8 POC and Integration
· Successful PoC in end-users premises (Carabinieri)
· Successful Field tests in end-users premises (using three systems located in PJ, Carabinieri and Airbus)
· Submission of D8.4 Integrated System prototype 1 (PoC)
· Submission of D8.5 Integrated System prototype 2 (First Field Tests)

WP9 Validation, Field Testing and End Users training
· Design and execution of POC evaluation
· Successful preparation and execution of the Field Test
· Ongoing End User training

WP10 Dissemination & Exploitation of Results, Certifications & Standardization Activities
· Publications of the SIIP consortium
· On-going maintenance and update of the SIIP public website and social media sites.
· Presentation of the SIIP project in many conferences and workshops
· POC event in Rome
· Field test in Lisbon
· Public descriptive SIIP movie
· POC documentary movie and album
· Field Test documentary movie and album
· Newsletters with the distribution list from the POC, Field test and web site registration.

WP11 Project Management
· Preparation and execution of the SIIP meetings
· Organising and facilitating all of the project's communication
· Placing a 2nd amendment of the GA
· Reviewing and submitting all deliverables
· Overviewing and performing quality control over all the project's activities
· Submission of interim and period reports
· Financial coordination
· Maintenance of the internal FTP servers
· Maintenance and update of the project's website
· Participating in the dissemination and use plan
· Coordination of press release distribution and catalogue publications

Potential Impact:
The SIIP technologies for voice biometrics and speaker identification have the ability to grant the LEAs an accurate and efficient method for suspects' identification. This technology has the potential to solve and prevent crimes, to shorten the time invested by LEAs, all leading to substantial savings in public costs. The work performed so far within the project is foreseen to significantly contribute to the entire field of speech recognition.
These enhanced tools of speech recognition are particularly relevant to fighting organized crime and terrorism, where this technology is an important tool in successfully prosecuting sophisticated criminals.
The expected social impact of the project is based on lower public costs incurred on investigations and lawsuits and overall enhanced security.

List of Websites:
http://www.siip.eu/

Reported by

VERINT SYSTEMS Ltd
Israel

Subjects

Safety
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top