logo Idiap Research Institute        
 [BibTeX] [Marc21]
SIIP: An Innovative Speaker Identification Approach for Law Enforcement Agencies
Type of publication: Conference paper
Citation: Khelif_STO-MP-IST-160_2018
Publication status: Published
Booktitle: Big Data and Artificial Intelligence for Military Decision Making
Year: 2018
Month: May
Pages: PT-1 - 1: PT-1 - 14
Publisher: STO
Organization: http://www.sto.nato.int/
Note: Meeting Proceedings RDP
ISBN: ISBN 978-92-837-2181-9
URL: https://www.sto.nato.int/publi...
DOI: 10.14339/STO-MP-IST-160
Abstract: This paper describes SIIP (Speaker Identification Integrated Project) a high performance innovative and sustainable Speaker Identification (SID) solution, running over large voice samples database. The proposed solution is based on development, integration and fusion of a series of individual speech analytic algorithms which includes speaker recognition, gender/age/language/accent identification, large vocabulary multilingual automatic speech-to-text transcription, expanded by keyword and taxonomy spotting. A full integrated system is proposed ensuring multisource data management, advanced voice analysis, information sharing and efficient and consistent man-machine interactions. The implemented system presented in this paper has been introduced to the international community of law-enforcement agencies animated by Interpol. Preliminary feedbacks collected from end-users indicate their satisfaction with the proposed architecture and its functionality. They also expressed different exploitation needs that we will try to take into account in a further work.
Projects Idiap
Authors Khelif, Khaled
yann Mombrun
Hazzani, Gideon
Motlicek, Petr
Madikeri, Srikanth
Sahito, Farhan
Kelly, Damien
Scarpatto, Luca
Chatzigavriil, Emmanouil
Backfried, Gerhard
Added by: [UNK]
Total mark: 0