Title :
Boosting HMMs with an application to speech recognition
Author :
Dimitrakakis, Christos ; Bengio, Samy
Author_Institution :
IDIAP, Martigny, Switzerland
Abstract :
Boosting is a general method for training an ensemble of classifiers with a view to improving performance relative to that of a single classifier. While the original AdaBoost algorithm has been defined for classification tasks, the current work examines its applicability to sequence learning problems, focusing on speech recognition. We apply boosting at the phoneme model level and recombine expert decisions using multi-stream techniques.
Keywords :
hidden Markov models; learning (artificial intelligence); pattern classification; signal classification; speech recognition; AdaBoost algorithm; HMM boosting; classifier training; hidden Markov models; multi-stream techniques; phoneme model; sequence learning problems; speech recognition; Algorithm design and analysis; Boosting; Decision making; Hidden Markov models; Iterative algorithms; Learning systems; Machine learning; Machine learning algorithms; Management training; Speech recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
Print_ISBN :
0-7803-8484-9
DOI :
10.1109/ICASSP.2004.1327187
