Fundamentals of speech recognition
Fundamentals of speech recognition
Embedded Bernoulli Mixture HMMs for Handwritten Word Recognition
ICDAR '09 Proceedings of the 2009 10th International Conference on Document Analysis and Recognition
ICDAR 2009 Handwriting Recognition Competition
ICDAR '09 Proceedings of the 2009 10th International Conference on Document Analysis and Recognition
Results of the RIMES Evaluation Campaign for Handwritten Mail Processing
ICDAR '09 Proceedings of the 2009 10th International Conference on Document Analysis and Recognition
ICFHR 2010 - Arabic Handwriting Recognition Competition
ICFHR '10 Proceedings of the 2010 12th International Conference on Frontiers in Handwriting Recognition
Windowed Bernoulli Mixture HMMs for Arabic Handwritten Word Recognition
ICFHR '10 Proceedings of the 2010 12th International Conference on Frontiers in Handwriting Recognition
Dynamic and Contextual Information in HMM Modeling for Handwritten Word Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Discriminative Bernoulli Mixture Models for Handwritten Digit Recognition
ICDAR '11 Proceedings of the 2011 International Conference on Document Analysis and Recognition
| Hi-index | 0.10 |
Bernoulli HMMs (BHMMs) have been successfully applied to handwritten text recognition (HTR) tasks such as continuous and isolated handwritten words. BHMMs belong to the generative model family and, hence, are usually trained by (joint) maximum likelihood estimation (MLE) by means of the Baum-Welch algorithm. Despite the good properties of the MLE criterion, there are better training criteria such as maximum mutual information (MMI). The MMI is the most widespread criterion to train discriminative models such as log-linear (or maximum entropy) models. Inspired by a BHMM classifier, in this work, a log-linear HMM (LLHMM) for binary data is proposed. The proposed model is proved to be equivalent to the BHMM classifier, and, in this way, a discriminative training framework for BHMM classifiers is defined. The behavior of the proposed discriminative training framework is deeply studied in a well known task of isolated word recognition, the RIMES database.