Patent
1991-12-20
1994-01-18
Fleming, Michael R.
G10L 900
Patent
active
052805638
ABSTRACT:
In a continuous speech recognizer which includes at least, one acoustic expert and one linguistic expert which generate respective scores, a method is disclosed for adjusting the relative weighting to be applied to those scores employing training data utilizing the words to be recognized in multiple word phrases. Multiple word test phrases are applied to the acoustic expert to determine, for each phrase, plural multi-word hypotheses each having corresponding cumulative scores. The linguistic expert generates corresponding cumulative linguistic scores. An objective function is calculated for each test phrase having a value which is variable as a function of the difference between the combined score of any correct hypothesis and that of the most easily confused incorrect hypothesis. The objective function values are cumulated and a gradient descent procedure is used to adjust the relative weighting of the acoustic and linguistic scores in obtaining a combined score.
REFERENCES:
patent: 4741036 (1988-04-01), Bahl et al.
patent: 4926488 (1990-05-01), Nadas et al.
Yen-Lu Chow--"Maximum Mutual Information Estimation of HMM Parameters or Continuous Speech Recognition Using the N-Best Algorithm"--1990 IEEE--pp. 701-704.
Doerrler Michelle
Fleming Michael R.
Kurzweil Applied Intelligence, Inc.
Pahl Jr. Henry D.
LandOfFree
Method of optimizing a composite speech recognition expert does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method of optimizing a composite speech recognition expert, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of optimizing a composite speech recognition expert will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1141921