10.15131/shef.data.3437426.v1
Oscar Saz Torralba
Oscar
Saz Torralba
Thomas Hain
Thomas
Hain
Julia Olcoz Martinez
Julia
Olcoz Martinez
Interspeech 2016 - Experiment results for paper "Error correction in lightly supervised alignment of broadcast subtitles"
The University of Sheffield
2016
Automatic Speech Recognition
Multimedia Data
Lightly Supervised Alignment
Interspeech 2016
Natural Language Processing
Artificial Intelligence and Image Processing
2016-06-22 09:37:16
Dataset
https://orda.shef.ac.uk/articles/dataset/Interspeech_2016_-_Experiment_results_for_paper_Error_correction_in_lightly_supervised_alignment_of_broadcast_subtitles_/3437426
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" <a href="https://doi.org/10.21437/Interspeech.2016-56">DOI: 10.21437/Interspeech.2016-56</a>.<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.