Real Time Processing with Low Latency

How Our Technology Works

The process of capturing radio and TV channels is fully automated: we offer 24/7 real-time monitoring, analyzing and keyword alerting typically on average 25 - 30 seconds after the broadcast.

Keep in mind that one of the characteristics of spoken language is that we need to wait for a sentence to be complete before we can analyze it!

Real Time

Real time is the time during which a process takes place or an event occurs; all our systems are engineered to work in real time and with low latency.

Real time means that whenever we process a piece of information, e.g. a 10-minute interview, we can finish the processing within those ten minutes. Using know-how from real-time-systems research, our systems are capable of delivering information within less than 30 seconds from the time a keyword was aired until we send out an alert to our users (by e-mail, instant messaging, or RSS feed).

Low Latency

Low latency describes the difference between the time when an information is aired/recorded and the time when it is processed. The delay (latency) is measured in seconds, depending on the system architecture and resources available. The eMM Pegasus System is specifically engineered to process incoming information as it streams in (stream-based processing) and all subsystems work with the information, once it arrives.

Find more information about the latest advances in technology:

> Deep Learning

> Audio Processing

> Video Processing

> Semantic Analysis