Project detail

Enabling automatic speaker verification to broad spectrum of users in the security domain

Duration: 01.04.2013 — 30.09.2015

Funding resources

Ministerstvo vnitra ČR - Program bezpečnostního výzkumu České republiky 2010 - 2015

- whole funder (2013-04-01 - 2015-09-30)

On the project

U rozpoznávání mluvčího (SRE) došlo v minulých letech k podstatnému teoretickému a algoritmickému pokroku. Projekt se soustředí na adaptaci algoritmů pro specifické potřeby policejních a zpravodajských složek, tak aby (1) poskytovaly precizní ale jednoduché zobrazení výsledků tak, aby zodpovědní pracovníci získali včas potřebnou informaci a udrželi si rychlost reakce proti hrozbám a ve vyšetřování, (2) je bylo možné dotrénovat na cílových datech uživatele a podstatně tak zvýšit jejich úspěšnost.

Description in English
Past few years have witnessed a substantial progress in theory and algorithimization of speaker recognition (SRE). This project aims at adaptation of SRE algorithms for specific needs of police and intelligence services, in order to (1) provide precise but easy-to-understand visualization so that responsible personnel obtains timely information needed to cope with threats and to speed up investigation, (2) be able to adapt systems to target user data and substantially improve their performances.

Keywords
rozpoznávání mluvčího; hlasová biometrie; vyhledávání mluvčího; hlasová analýza; forenzní analýza

Key words in English
speaker recognition; voice biometry; speaker search; voice analysis; forensic analysis

Mark

VG20132015129

Default language

Czech

People responsible

Glembek Ondřej, Ing., Ph.D. - fellow researcher
Kobes Michal - fellow researcher
Kohlová Renata, Ing. - fellow researcher
Pešán Jan, Ing. - fellow researcher
Plchot Oldřich, Ing., Ph.D. - fellow researcher
Šimek Dominik, Ing. - fellow researcher
Veselý Karel, Ing., Ph.D. - fellow researcher
Černocký Jan, prof. Dr. Ing. - principal person responsible

Units

Department of Computer Graphics and Multimedia
- beneficiary (2011-05-06 - 2015-09-30)

Results

KHOURY, E.; VESNICER, B.; FRANCO-PEDROSO, J.; DIEZ SÁNCHEZ, M.; CIPR, T.; SCHWARZ, P.; VAN LEEUWEN, D.; PETROVSKA-DELACRETAZ, D.; MATĚJKA, P.; RODRIGUEZ-FUENTES, L.; CHOLLET, G.; MARCEL, S. The 2013 Speaker Recognition Evaluation in Mobile Environment. Proceedings of Biometrics (ICB), 2013 International Conference on. Madrid: IEEE Biometric Council, 2013. p. 1-8. ISBN: 978-1-4799-0310-8.
Detail

PLCHOT, O.; DIEZ SÁNCHEZ, M.; SOUFIFAR, M.; BURGET, L. PLLR Features in Language Recognition System for RATS. In Proceedings of Interspeech 2014. Singapore: International Speech Communication Association, 2014. p. 3048-3051. ISBN: 978-1-63439-435-2.
Detail

FÉR, R.; MATĚJKA, P.; GRÉZL, F.; PLCHOT, O.; ČERNOCKÝ, J. Multilingual Bottleneck Features for Language Recognition. In Proceedings of Interspeech 2015. Proceedings of Interspeech. Dresden: International Speech Communication Association, 2015. p. 389-393. ISBN: 978-1-5108-1790-6. ISSN: 1990-9772.
Detail

GLEMBEK, O.; MATĚJKA, P.; BURGET, L.; SCHWARZ, P.; PEŠÁN, J.; PLCHOT, O. Voice-print transformation for migration between automatic speaker identification systems. Abstract book of the 7th European Academy of Forensic Science Conference. Praha: Criminal Police Department Prague, 2015. p. 345-345. ISBN: 978-80-260-8659-8.
Detail

SILNOVA, A.; GLEMBEK, O.; KINNUNEN, T.; MATĚJKA, P. Exploring ANN Back-Ends for i-Vector Based Speaker Age Estimation. In Proceedings of Interspeech 2015. Proceedings of Interspeech. Dresden: International Speech Communication Association, 2015. p. 3036-3040. ISBN: 978-1-5108-1790-6. ISSN: 1990-9772.
Detail

LOPEZ-MORENO, I.; GONZALEZ-DOMINGUEZ, J.; MARTÍNEZ GONZÁLEZ, D.; PLCHOT, O.; GONZALEZ-RODRIGUEZ, J.; MORENO, P. On the use of deep feedforward neural networks for automatic language identification. COMPUTER SPEECH AND LANGUAGE, 2016, vol. 2016, no. 40, p. 46-59. ISSN: 0885-2308.
Detail

CUMANI, S.; PLCHOT, O.; FÉR, R. Exploiting i-vector posterior covariances for short-duration language recognition. In Proceedings of Interspeech 2015. Proceedings of Interspeech. Dresden: International Speech Communication Association, 2015. p. 1002-1006. ISBN: 978-1-5108-1790-6. ISSN: 1990-9772.
Detail

Responsibility: Černocký Jan, prof. Dr. Ing.