The noise robustness of automatic speech recognition systems can be increased by transforming the signal to make the cumulative density functions of the signal’s values in recognition match the ones that where estimated on the training data. This paper describes a real-time online algorithm to approximate the cumulative density functions, after Mel scaled filtering, using a small number of quantiles. Recognition tests where carried out on the Aurora noisy TI digit strings and SpeechDat-Car databases. The average relative reduction of the word error rates was 32% on the noisy TI digit strings and 29% on SpeechDat-Car.