Confidence estimation in speech recognition

In the Automatic Speech Recognition (ASR) systems, the capability to evaluate result reliability is extremely important for speech application usage. Thus, in many real-world applications with ambient noise, speaker variations, channel distortions etc, confidence measure must be computed for any recognition decision made by ASR systems. In this paper, with reference to earlier research work, we presented a techniques for estimating confidence measures using the acoustic normalization or phone recognizer in conjunction with the word recognizer for Serbian language.