How the Speech to Text Module works
22 November, 2016
MAM Software VIDEOMA, also available on Cloud
13 December, 2016


Discover our most Advanced Analyzing Technologies

Videoma brings its Automatic People Recognition System to the most demanding users within the Security, Public Administrations and Corporate sectors being able to carry out the most complete and thorough Forensic Multimedia Analysis.

The face recognition system is done through the analysis of the source directly or through the forensic analysis of an audiovisual archive.

The detection and later face recognition is a very efficient process, where its technology allows changes in facial expression, lighting and presence of glasses, beard, scarves, or hats.

The recognition content is added to the Database, providing the exact timecode and frame from where the information was extracted. The relationship between the video and its analysis is complete, allowing you to position yourself in the exact identification moment.

The system is also capable of identifying different voices and its speakers within the archive video and audio collections. The system lastly provides a quality score of its recognition for its storage.

Speaker Recognition through its tone of voice is a technology frequently used in Call Centers and Security environments. The system integrates in the same way as to how the Facial Recognition system works.

The precision and speed of the system is very high, allowing comparisons of 1: Millions with great accuracy and very rapidly.