Multi-channel biometrics combining acoustic and machine vision analysis of speech, lip movement and face

Informazioni relative al progetto

SpeechXRays

ID dell’accordo di sovvenzione: 653586

DOI

10.3030/653586

Progetto chiuso

Data della firma CE 30 Aprile 2015

Data di avvio 1 Maggio 2015

Data di completamento 30 Aprile 2019

Finanziato da

• Secure societies - Protecting freedom and security of Europe and its citizens

Costo totale

€ 5 278 189,82

Contributo UE

€ 4 102 467,00

Coordinato da

IDEMIA FRANCE
France

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (26)

User interface implementation report

Formative evaluation of the system’s user interfaces, for both and users and administrators.

Consumer Use Case Recruitment

Specifications of recruitment procedure for Use Testing including the end user consent form and all procecedure set to ensure security and privacy.

Consumer pilot implementation report

report about recruitment of participants, assessments, and execution of the Consumer use case pilot.

System architecture

Specification of the information flow between the different system components and the integration requirements.

Compilation of standard contributions

Report about contributions to the development of the ISO/IEC 19794-13 standard, currently in Committee Draft status with target publication date 2016-01-04 (Table 12).

Workfoce use case recruitment

Specifications of recruitment procedure for Use Testing including the end user consent form and all procecedure set to ensure security and privacy.

Ecosystem report

Report about activities that will promote the project technologies and innovations to the market, and intended to create an ecosystem around the SpeechXRays solution.

Workforce pilot implementation report

Report about the will implementation the solution on numerous users of mobile devices: level of security, threat remediation and adaptability of the solution to various application (online access, physical perimeter access).

eHalth use case description

Public Version of D1.2

Spoofing contest report

Report about dissemination activities organised to support a spoofing contest

Final (Public) Report

Report communication between the Consortium and the Commission concerning project progress and execution of the Contract, financial accounting within the Consortium, and between the Consortium and the Commission. progress reporting within the Consortium by Work package.

Workforce Use case Description

Public version of deliverable D1.1.

System interoperability report

Evaluation report of the integrated software platform interoperable with other software systems and/or external data sources

Test/QA report

The report will described how the developed software integration platform is fulfilling stakeholders’ expectations.

Validation report

Results of validation and test of the multichannel biometrics

User physiology impact report

impact of the user physiology on the solution performance

Consumer use case description

Public version of D1.3

eHealth use case Recruitment

Specifications of recruitment procedure for Use Case Testing including the end user consent form and all procecedure set to ensure security and privacy.

Report on published standards

Analysing of published standards such as ISO/IEC 19794-5:2011 and ANSI/NIST-ITL 1-2011.

Developer contest report

Report of dissemination activities organised in support of application development contest

Collaboration report

Report about cross-fertilization activities with ongoing FP7-ICT or FP7-SECURITY projects and new Horizon 2020 projects focusing on similar challenges.

Pilot Evaluation Report

This report will gather the evaluation of each use case gathering the outputs about technology efficiency, security enforcement and user acceptance

Dissemination report

regular progress reports and list of articles published

Business cases

Description of industrial business cases development for the targeted applications, including return on investment (ROI) and cost-benefit analyses (CBA).

eHealth pilot implementation report

report about recruitment of participants, assessments, and execution of the eHealth use case pilot.

Reports on industry workshops

promote the project results to companies external to the consortium, by arranging 3 workshops in relation with the 3 pilots.

Demonstrators, pilots, prototypes (4)

System release v3

system integrating multichannel biometric component and user interfaces

System release v1

system integrating multichannel biometric component and security/privacy component

System release v2

system integrating multichannel biometric component and user interface.

Context-dependent tuning framework

A framework in which the matching threshold can be adapted based on the level of security required by the service that the user is attempting to access

Other (3)

Face identification method

A face recognition reference system

Audio-visual analysis method

Descriptors of lips will be interpolated to match the speech spectrum sampling rate (100 Hz).

Voice acoustics recognition method

A feature vector containing acoustic correlates of voice quality

Websites, patent fillings, videos etc. (2)

Standard workshop agreement

UCL will develop a Workshop Agreement (also known as CWA) in the area of multichannel biometrics combining dynamic voice and face identification

External project website

an external project website hosted at www.speechxrays.eu. The website will include a description of the project, the consortium and the industrial demonstrators

Pubblicazioni

Conference proceedings (8)

Full Video Processing for Mobile Audio-Visual Identity Verification

Autori: Alexander Usoltsev, Dijana Petrovska-Delacrétaz, Khemiri Houssemeddine
Pubblicato in: Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods, 2016, Pagina/e 552-557, ISBN 978-989-758-173-1
Editore: SCITEPRESS - Science and and Technology Publications
DOI: 10.5220/0005667305520557

Testing voice-based biometrics authentication platforms for Romanian utterances through infrequent consonant clusters

Autori: A. Cocioceanu, M. Barbulescu, T. Ivanoaica, M. Raportaru, A. I. Nicolin
Pubblicato in: 2016 15th RoEduNet Conference: Networking in Education and Research, 2016, Pagina/e 1-4, ISBN 978-1-5090-5398-8
Editore: IEEE
DOI: 10.1109/RoEduNet.2016.7753205

Cohort selection for text-dependent speaker verification score normalization

Autori: Houssemeddine Khemiri, Dijana Petrovska-Delacretaz
Pubblicato in: 2016 2nd International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2016, Pagina/e 689-692, ISBN 978-1-4673-8526-8
Editore: IEEE
DOI: 10.1109/ATSIP.2016.7523167

Secure access to patient's health records using SpeechXRays a mutli-channel biometrics platform for user authentication

Autori: Emmanouil G. Spanakis, Marios Spanakis, Apostolos Karantanas, Kostas Marias
Pubblicato in: 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016, Pagina/e 2541-2544, ISBN 978-1-4577-0220-4
Editore: IEEE
DOI: 10.1109/EMBC.2016.7591248

Redesign of Gaussian Mixture Model for Efficient and Privacy-preserving Speaker Recognition

Autori: S Rahulamathavan, X Yao, R Yogachandran, K Cumanan, M Rajarajan
Pubblicato in: 2018 International Conference On Cyber Situational Awareness, Data Analytics And Assessment (Cyber SA), 2018, Pagina/e 1-8, ISBN 978-1-5386-4565-9
Editore: IEEE
DOI: 10.1109/cybersa.2018.8551477

Cancelable speaker verification system based on binary Gaussian mixtures

Autori: Aymen Mtibaa, Dijana Petrovska-Delacretaz, Ahmed Ben Hamida
Pubblicato in: 2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2018, Pagina/e 1-6, ISBN 978-1-5386-5239-8
Editore: IEEE
DOI: 10.1109/ATSIP.2018.8364513

State-of-the-art face recognition performance using publicly available software and datasets

Autori: Mohamed Amine Hmani, Dijana Petrovska-Delacretaz
Pubblicato in: 2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2018, Pagina/e 1-6, ISBN 978-1-5386-5239-8
Editore: IEEE
DOI: 10.1109/ATSIP.2018.8364450

Computer-based statistical description of phonetical balance for Romanian utterances

Autori: Cocioceanu, Adrian; Ivanoaica, Teodor; Nicolin, Alexandru; Raportaru, Mihaela Carina
Pubblicato in: International Conference on ICT Innovations, Numero 1, 2016, Pagina/e 59--67
Editore: springer
DOI: 10.5281/zenodo.399071

Peer reviewed articles (2)

Privacy-Preserving iVector-Based Speaker Verification

Autori: Yogachandran Rahulamathavan, Kunaraj R Sutharsini, Indranil Ghosh Ray, Rongxing Lu, Muttukrishnan Rajarajan
Pubblicato in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Numero 27/3, 2019, Pagina/e 496-506, ISSN 2329-9290
Editore: IEEE Advancing Technology for Humanity
DOI: 10.1109/taslp.2018.2882731

Technology-Based Innovations to Foster Personalized Healthy Lifestyles and Well-Being: A Targeted Review

Autori: Emmanouil G Spanakis, Silvina Santana, Manolis Tsiknakis, Kostas Marias, Vangelis Sakkalis, António Teixeira, Joris H Janssen, Henri de Jong, Chariklia Tziraki
Pubblicato in: Journal of Medical Internet Research, Numero 18/6, 2016, Pagina/e e128, ISSN 1438-8871
Editore: Journal of medical Internet Research
DOI: 10.2196/jmir.4863