Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
2006-03-16
2010-10-12
Hudspeth, David R (Department: 2626)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S243000, C704S244000, C704S257000
Reexamination Certificate
active
07813926
ABSTRACT:
A training system for a speech recognition application is disclosed. In embodiments described, the training system is used to train a classification model or language model. The classification model is trained using an adaptive language model generated by an iterative training process. In embodiments described, the training data is recognized by the speech recognition component and the recognized text is used to create the adaptive language model which is used for speech recognition in a following training iteration.
REFERENCES:
patent: 5960397 (1999-09-01), Rahim
patent: 2003/0212543 (2003-11-01), Epstein et al.
patent: 2007/0156392 (2007-07-01), Balchandran et al.
“Unsupervised Language Model Adaptation” by Bacchiani et al., AT&T Labs-Research, IEEE 2003, pp. I-224 through I-227.
Wang et al., “Speech Utterance Classification Model Training Without Manual Transcriptions”, Proc. ICASSP 2006, Toulouse, France, May 2006; pp. I-553-I-556.
Acero Alex
Lee John Sie Yuen
Wang Ye-Yi
Hudspeth David R
Kelly Joseph R.
Microsoft Corporation
Rider Justin W
Westman Champlin & Kelly P.A.
LandOfFree
Training system for a speech recognition application does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Training system for a speech recognition application, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Training system for a speech recognition application will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4179250