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.

Abstract: A recognition criterion or set of recognition criteria are updated automatically, over time, in accordance with the speech input of the user(s). Each input utterance is compared to one or more models of speech to determine a similarity metric for each such comparison. A 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 selected set of recognition criteria. The recognition criteria are automatically altered during use or "on-the-fly", so that more appropriate criteria (and associated thresholds) may be used to either increase the probability of recognition or decrease the incidence of false positive results. Illustratively, if a voice sample results in a near miss of a template, a more liberal criterion is thereafter employed to increase the probability of recognition for subsequent input.