International Business Machines Corporation

Kris A Coe

Kerry Alan Ortega

Maria Elena Smith

Burn Lewin Lewis

Kyriakos L Leontiades

Steven J Friedland

A method for automatically analyzing a document in a speech recognition system having a vocabulary and language model can include the steps of: determining whether the document has undergone previous analysis; undoing the previous analysis; and, analyzing the document. More specifically, the determining step comprises the steps of: comparing trigrams in the document with trigrams in the language model; and, setting a reference point containing document data for undoing a previous analysis in the undoing step if the compared language model contains all the document trigrams. Moreover, the undoing step comprises the step of removing from the language model each trigram contained in the document data in the reference point. Finally, the analyzing step comprises the steps of: searching the document for new words not contained in the vocabulary; adding said new words to said vocabulary; updating the language model with trigrams contained in the document; and, setting a reference point containing document data for undoing the updating of the language model in the updating step. In addition, the adding step can comprise identifying among the new words found in the searching step, correctly-spelled words not requiring a speaker-supplied pronunciation; and adding the correctly-spelled words to the vocabulary. The inventive method can further comprise the steps of: recognizing a request from a user of the speech dictation system to discontinue user editing; finding in the document new words not contained in the vocabulary in response to the request; enhancing the vocabulary with the new words; undoing the analysis created during the analyzing step; and, further analyzing the document.

Automatic analysis of a speech dictated document

A computer voice operated dictations system having a text editing mode provided for editing dictated text. The text editing mode navigates a user through the dictated text by highlighting a correction window comprised of a plurality of words comprising a portion of the text. The correction window is comprised of 'm' words and the value of m is preferably determined, based upon the voice recognition capabilities of a particular voice recognition engine associated with the dictation system. The greater the ability of the speech recognition engine to recognize and distinguish spoken words, the larger the value of m. A correction vocabulary is defined which consists of the plurality of words which are contained within the correction window and a plurality of correction commands. The voice recognition computer dictation system is configured for processing a spoken utterance which corresponds to an error word contained within the plurality of words highlighted in the correction window is processed. When the error word is spoken by a user it uniquely identifies the word which is to be edited. Thereafter, the error word can be immediately corrected by the user articulating a further voice command.

Growing community of inventors

Lighthouse Point, FL, United States of America

Kris A Coe