Barbara E. Ballard

Method and apparatus for intelligently managing multiple pronunciations for a speech recognition vocabulary

In a computer speech dictation system, a method for automatically managing a plurality of acoustic models. The method is intended to ensure that only high reliability acoustic models which accurately reflect word pronunciations for a given user are retained. The method is accomplished by assigning a base quality metric value for each of the acoustic models maintained by a speech recognition application. The quality metric is incremented or decremented upon the occurrence of certain events relevant to the reliablity of the acoustic model. Acoustic model are discarded when the quality metric value falls below a threshold value.