In order to facilitate language acquisition, when language learners speak incomprehensible utterances, a Dialog-based Computer Assisted Language Learning (DB-CALL) system should provide matching fluent utterances by inferring the actual learner’s intention both from the utterance itself and from the dialog context as human tutors do. We propose a hybrid inference model that allows a practical a...

Received views of utterance context in pragmatic theory characterize the occurrent subjective states of interlocutors using notions like common knowledge or mutual belief. We argue that these views are not compatible with the uncertainty and robustness of context-dependence in human–human dialogue. We present an alternative characterization of utterance context as objective and normative. This ...

Cepstral Mean Normalization (CMN) is a widely used technique for channel compensation and for noise robustness. CMN compensates for noise by transforming both train and test utterances to zero mean, thus matching first-order moment of train and test conditions. Since all utterances are normalized to zero mean, CMN could lead to loss of discriminative speech information, especially for short utt...

Optimal accentuation of a sentence involves accentuating a minimal set of words which in a given context suffices for understanding the entire sentence. We propose a model of the interpretation of incomplete or not entirely recognized utterances. Using this model, we determine which constituents of an utterance have to be accentuated given a certain context. 1. Optimal Accentuation Our basic as...

the language used by women and men differ in all speech communities. in order to examine some of these variations, the present study aimed to investigate the differences in an informal written discourse. for this purpose, a comparison between men’s and women’s informal language was made regarding length of utterances, questions, intensifiers, and hedges. results revealed that men employed highe...