Sentence examples for template representative from inspiring English sources

In Section 4, we discuss the proposed methods for template representative selection and compression.

This indicates that the new GMMs were more effective in labeling the template representative frames, and the exclusion of the outlier GMMs was helpful, too.

The number of GMM clusters l in MLTS was set to 5, corresponding to using five GMMs to label each frame of a template representative.

This difference may be explained by the fact that MDTS simply selects a cluster center as a template representative, but MLTS further refines the GMM indices of each template representative frame to maximize the likelihood of the aligned frames in the corresponding cluster.

To select a template representative for a cluster, we use the minimum distance from a template to all other templates in the cluster as the criterion, and therefore the method is called minimum distance template selection (MDTS).

The remaining Gaussian components are used to construct a new GMM, and the new GMM is used as one of the l GMMs to label the corresponding frame of the template representative.

Generating template representatives and representing the frames by GMM indices make the approach extendable to LVCSR task.

We further propose to fine tune the MLTS template representatives by using a GMM merging algorithm so that the GMMs can better represent the frames of the selected template representatives.

In addition, the memory overhead for all five doctors was around 236.2, 47.2, and 73.2 MB for using all templates, selected template representatives, and compressed template representatives, respectively.

Here the number of template representatives was kept to be 20% of total templates.

The template compression method aims at taking in more information from the original templates for the template representatives.