Interspeech 2016 - Experiment results for paper "Error correction in lightly supervised alignment of broadcast subtitles"

The files in the dataset correspond to results that have been generated for the Interspeech 2016 article: "Error correction in lightly supervised alignment of broadcast subtitles" DOI: 10.21437/Interspeech.2016-56.<br> <br> The files in the zip file are of two types:<br> - .ctm, which correspond to the output of the lightly supervised alignment system.<br> - .sys, which correspond to scoring of the lightly supervised alignment system and includes the overall F measure as well as the precision and recall of the overall system and of each individual show.<br> <br>The following is a description about the naming convention of the files:<br> <br>TableX-LineY: This is the alignment and scoring output corresponding to Line Y of Table X in the article.<br>TableX-LineY-[dev|eval]: This is the alignment and scoring output corresponding to Line Y of Table X for development (dev) or evaluation (eval) in the article.<br> <br> All two file types are standard outputs that are recognised by the speech technology community and can be opened using any text editor.