Interspeech 2016 - Experiment results for paper "webASR 2 - Improved cloud based speech technology"

Abstract

The files in the dataset correspond to results that have been generated for the Interspeech 2016 article: "webASR 2 - Improved cloud based speech technology" DOI: 10.21437/Interspeech.2016-700.

The files included are of several types:
- .ctm, which correspond to the output of an automatic speech recognition system.
- .rttm, which correspond to the output of a speaker diarisation system.
- .moses which correspond to the output of a machine translation system
- .sys, which correspond to the scoring results of the corresponding system.

The following is a description about the naming convention of the files:

TableX-LineY: This is the output and scoring results corresponding to Line Y of Table X in the article.

All file types are standard outputs that are recognised by the speech technology community and can be opened using any text editor.