Real time factor

The real time factor (RTF) is a common metric of measuring the speed of an automatic speech recognition system. It can also be used in other context where an audio or video signal is processed (usually automatically) at nearly constant rate (e.g. reading music from a CD).

Definition

If it takes time ${P}$ to process an input of duration ${I}$ , the real time factor is defined as

$RTF = \frac{P}{I}$ .

If, for example, it takes 8 hours of computation time to process a recording of duration 2 hours, the real time factor is 4. When the real time factor is 1 or less than 1 , the processing is done in real time. It is a hardware-dependent value.

The accuracy of a speech recognition system, on the other hand, is measured with the word error rate.