Prosody/Parse Scoring and Its Application in ATIS
BOSTON UNIV MA DEPT OF ELECTRICAL AND COMPUTER ENGINEERING
Pagination or Media Count:
Prosodic patterns provide important cues for resolving syntactic ambiguity, and might be used to improve the accuracy of automatic speech understanding. With this goal, we propose a method of scoring syntactic parses in terms of oh served prosodic cues, which can be used in ranking sentence hypotheses and associated parses. Specifically, the score is the probability of acoustic features of a hypothesized word sequence given an associated syntactic parse, based on acoustic and language prosodysyntax models that represent probabilities in terms of abstract prosodic labels. This work reports initial efforts aimed at extending the algorithm to spontaneous speech, specifically the ATIS task, where the prosodyparse score is shown to improve the average rank of the correct sentence hypothesis.