Improving rejection with semantic slot-based confidence scores

This paper introduces a new confidence scoring mechanism which takes advantage of the semantic parsing provided by a natural language understanding system. As a result, different segments of the user input which fill individual semantic slots are identified and individual semantic slot confidence scores are generated. With slot-based confidence scores, each individual slot receives a confidence score generated by combining the confidence scores of the individual words which fill that particular slot. With judicious use of confidence scores for individual slots, better rejection and more natural interaction with the system are achieved.

[1]  James R. Glass,et al.  Confidence scoring for speech understanding systems , 1998, ICSLP.

[2]  Biing-Hwang Juang,et al.  Key-phrase detection and verification for flexible speech understanding , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[3]  Michael Cohen,et al.  A phone-dependent confidence measure for utterance rejection , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[4]  Vassilios Digalakis,et al.  Genones: generalized mixture tying in continuous hidden Markov model-based speech recognizers , 1996, IEEE Trans. Speech Audio Process..