Integration of diverse recognition methodologies through reevaluation of N-best sentence hypotheses
HLT '91 Proceedings of the workshop on Speech and Natural Language
TINA: a natural language system for spoken language applications
Computational Linguistics
Pitch accent in context: predicting intonational prominence from text
Artificial Intelligence - Special volume on natural language processing
Multi-site data collection for a spoken language corpus
HLT '91 Proceedings of the workshop on Speech and Natural Language
DARPA February 1992 ATIS benchmark test results
HLT '91 Proceedings of the workshop on Speech and Natural Language
The MIT ATIS system: February 1992 progress report
HLT '91 Proceedings of the workshop on Speech and Natural Language
A relaxation method for understanding spontaneous speech utterances
HLT '91 Proceedings of the workshop on Speech and Natural Language
Using prosody to improve automatic speech recognition
Speech Communication
Speech recognition supported by prosodic information for fixed stress languages
TSD'07 Proceedings of the 10th international conference on Text, speech and dialogue
Using prosody in fixed stress languages for improvement of speech recognition
COST 2102'07 Proceedings of the 2007 COST action 2102 international conference on Verbal and nonverbal communication behaviours
Using prosodic features in language models for meetings
MLMI'07 Proceedings of the 4th international conference on Machine learning for multimodal interaction
Hi-index | 0.00 |
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 observed 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" (prosody/syntax) 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 prosody/parse score is shown to improve the average rank of the correct sentence hypothesis.