database
Perfiles para todos los ciudadanos y visitantes
entries with personal information entries with personal informationentries with personal informationentries with personal informationentries with personal informationentries with personal informationvv
data processing
Integración con la infraestructura de monitoreo existente
- automatic search of pure speech in audio files
- detecting number of speakers
- speaker separation (up to 5 speakers per audio channel)
- building biometric voiceprints of speakers
- gender and age identification
- language identification
- speech recognition (speech-to-text)
- automatic translation to arabic
- building biometric faceprints by photo from integrated external sources
search & identification
Multimodal automated search
- hotlists of target people
- topics of conversations
- keyword lists
- biometric database search, both by photo and recording
- archive search by voiceprint & faceprint.
- simultaneously in camera detections archive and recordings archive
- stream search by voiceprint & faceprint in incoming data
Route Mapping
link and object analysis in different display modes: link graphs and maps near-realtime face and voice tracking different types of reports for the tasks of identifying suspects and persons who potentially pose a threat detection of presence and stay-time determination of the visual target in the control area
analytics & clusterization
Clusterization of audio recordings using the speech recognition results
- cluster analysis of large arrays of data
- graphic visualization of connections between persons and related information
- statistical analysis by speakers, topics, location
- implicit links detection
- data display on local map (if data and cartography is available)
have any questions?
wondering if STC Group is the right tool for your business? Chat with our team to see if there’s a fit.
Request call
want to calculate the project?
contact our manager and get a detailed consultation on the costs and specifics of IKAR Lab 3 implementation
Write us