Distinguishing Questions by Contour Speech Recognition Tasks

It is generally acknowledged today that, while the intonational features speakers select when they utter a sentence are not determined by the syntax, semantics or discourse context of that sentence, knowledge of these factors can help to constrain the possible intonational features speakers are likely to choose. So, while intonational variation poses a challenge to speech recognition in one sense in presenting yet another indicator of over-all utterance meaning to be recognized regularities noted between intonational features and the syntax, semantics and discourse features of an utterance also present rich possibilities for help in the recognition task. The many-to-many mapping between intonational features and syntactic and discourse features can be illustrated by considering the various ways of uttering the sentences in (1). 1