Importance

Loading Importance Indicators...

Abstract

A method and apparatus for speech recognition in which a single criterion or set of criteria is selected manually by the user, from plural classes of recognition criteria. The stored classes of recognition criteria include a default class optimized for an average user in normal conditions, at least one class having a probability of recognition greater than said default class, and at least one class having a probability of recognition less than said default class. Accordingly, the user may select that class of criteria which provides the best results for him or her, as measured by greater accuracy (fewer false positive detections) or fewer instances of non-rejection. An utterance is compared to one or more models of speech to determine a similarity metric for each such comparison. The model of speech which most closely matches the utterance is determined based on the one or more similarity metrics. The similarity metric corresponding to the most closely matching model of speech is analyzed to determine whether the similarity metric satisfies the criteria of the user-selected class. The present application has application to many problems in speech recognition including isolated word recognition and command spotting. Illustrative embodiments of the invention in the context of telecommunications instruments are provided.

Loading the Abstract Image...

First Claim