Attention, intentions, and the structure of discourse
Computational Linguistics
High level knowledge sources in usable speech recognition systems
Communications of the ACM
Trends in Speech Recognition
Understanding goal-based stories.
Understanding goal-based stories.
Large-vocabulary speaker-independent continuous speech recognition: the sphinx system
Large-vocabulary speaker-independent continuous speech recognition: the sphinx system
Interactive natural language problem solving: a pragmatic approach
ANLC '83 Proceedings of the first conference on Applied natural language processing
Parsing spoken language: a semantic caseframe approach
COLING '86 Proceedings of the 11th coference on Computational linguistics
Flexible parsing of discretely uttered sentences
COLING '82 Proceedings of the 9th conference on Computational linguistics - Volume 1
Human Problem Solving
| Hi-index | 0.01 |
When computer speech recognition is used for problem solving or any plan based task, predictable features of the user's behavior may be inferred and used to aid the recognition of the speech input. The MINDS system generates expectations of what will be said next and uses them to assist speech recognition. Since a user does not always conform to system expectations, MINDS handles violated expectations. We use pragmatic knowledge to dynamically derive constraints about what the user is likely to say next. Then we loosen the constraints in a principled manner to generate layered sets of predictions which range from very specific to very general. To enable the speech system to give priority to recognizing what a user is most likely to say, each prediction set dynamically generates a grammar which is used by the speech recognizer. A different set of grammars is created after each user utterance. The grammars are tried in order of most specific first, until an acceptable parse is found. This allows optimal performance when users behave predictably, and displays graceful degradation when they do not.