Title :
Discriminative model combination
Author :
Beyerlein, Peter
Author_Institution :
Philips Res. Lab., Aachen, Germany
Abstract :
Discriminative model combination is a new approach in the field of automatic speech recognition. It aims at an optimal integration of all given (acoustic and language) models into one log-linear posterior probability distribution. As opposed to the maximum entropy approach, the coefficients of the log-linear combination are estimated on training samples using discriminative methods to obtain an optimal classifier
Keywords :
modelling; pattern classification; probability; speech recognition; acoustic models; automatic speech recognition; coefficient estimation; discriminative model combination; language models; log-linear posterior probability distribution; optimal classifier; optimal model integration; training samples; Automatic speech recognition; Entropy; Error analysis; Humans; Laboratories; Parameter estimation; Probability distribution;
Conference_Titel :
Automatic Speech Recognition and Understanding, 1997. Proceedings., 1997 IEEE Workshop on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-7803-3698-4
DOI :
10.1109/ASRU.1997.659011
