Further Experiments with Detector-Based Conditional Random Fields in Phonetic Recognition

Jeremy Morris, Eric Fosler-Lussier
2007 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07  
My dissertation work has focused on discriminative models for Automatic Speech Recognition (ASR), and I am also interested in the more general area of discriminative models for Natural Language Processing (NLP). At a more abstract level I am interested in the challenges of machine learning for integrating multiple streams of possibly highly correlated information.
doi:10.1109/icassp.2007.366944 dblp:conf/icassp/MorrisF07 fatcat:es2zpjryi5hvja2g5gvbu7u4jq