Results 1 
3 of
3
Implementing and improving MMIE training
 in SphinxTrain,” CMU Sphinx Workshop for Users and Developers (CMUSPUD
, 2010
"... Discriminative training schemes, such as Maximum Mutual Information Estimation (MMIE), have been used to improve the accuracy of speech recognition systems trained using Maximum Likelihood Estimation (MLE). In this paper, we present the implementation details of MMIE training in SphinxTrain and base ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Discriminative training schemes, such as Maximum Mutual Information Estimation (MMIE), have been used to improve the accuracy of speech recognition systems trained using Maximum Likelihood Estimation (MLE). In this paper, we present the implementation details of MMIE training in SphinxTrain and baseline results for MMIE training on the Wall Street Journal (WSJ) SI84 and SI284 data sets. This paper also introduces an efficient lattice pruning technique that both speeds up the process and increases the impact of MMIE training on recognition accuracy. The proposed pruning technique, based on posterior probability pruning, is shown to provide better performance than MMIE using standard pruning techniques. Index Terms — SphinxTrain, MMIE training, word lattice, lattice pruning 1.
The Effect of Lattice Pruning on MMIE Training
"... In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word lattice is usually used as a compact representation of many different sentence hypotheses and hence provides an efficient representation of the confusion data. However, in a large vocabulary continuous ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word lattice is usually used as a compact representation of many different sentence hypotheses and hence provides an efficient representation of the confusion data. However, in a large vocabulary continuous speech recognition (LVCSR) system trained from hundreds or thousands hours training data, the extended BaumWelch (EBW) computation on the word lattice is still very expensive. In this paper, we investigated the effect of lattice pruning on MMIE training, where we tested the MMIE performance trained with different lattice complexity. A beam pruning and a posterior probability pruning method were applied to generate different sizes of word lattices. The experimental results show that using the posterior probability lattice pruning algorithm, we can save about 40 % of the total computation and get the same or more improvement compared to the baseline MMIE result. Index Terms — MMIE training, word lattice, lattice pruning 1.
A Simplification Algorithm for Visualizing the Structure of Complex Graphs
"... Complex graphs, ones containing thousands of nodes of high degree, are difficult to visualize. Displaying all of the nodes and edges of these graphs can create an incomprehensible cluttered output. This paper presents a simplification algorithm that may be applied to a complex graph in order to prod ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Complex graphs, ones containing thousands of nodes of high degree, are difficult to visualize. Displaying all of the nodes and edges of these graphs can create an incomprehensible cluttered output. This paper presents a simplification algorithm that may be applied to a complex graph in order to produce a controlled thinning of the graph. Using importance metrics, the simplification process removes nodes from the graph, leaving the central structure for visualization and evaluation. The simplification algorithm consists of two steps, calculation of the importance metrics and pruning. Several metrics based on various topological graph properties are described. The metrics are then used in a pruning process to simplify the graph. Nodes, along with their corresponding edges, are removed from the graph, while maintaining the graph’s overall connectivity. This simplified graph provides a cleaner, more meaningful visual representation of the graph’s structure; thus aiding the analysis of the graph’s underlying data. 1