Incorporating a novel confidence scoring method in a Persian spoken dialogue system

Reliability assessment of phonemes, syllabi, words, concepts or utterances has become the key feature of Automatic Speech Recognition (ASR) engines in order to make a decision to accept or reject a hypothesis. In this paper, we propose utterance-level confidence annotation based on combination of features extracted from multiple knowledge sources in Persian language. The experiment was conducted first to examine the performance of individual features, then to combine them using statistical data analysis and density estimation methods to assign a confidence score to utterances. Using the data collected from a Persian spoken dialogue system, we show that combining features from independent sources for confidence measure (CM) results in an improvement of about 5.5% mean error rate reduction in comparison to exploiting single features.