Computer, Speech and Language - Experiment results for paper "Acoustic Adaptation to Dynamic Background Conditions with Asynchronous Transformations"
datasetposted on 04.07.2016 by Oscar Saz Torralba, Thomas Hain
Datasets usually provide raw data for analysis. This raw data often comes in spreadsheet form, but can be any collection of data, on which analysis can be performed.
The files in the dataset correspond to results that have been generated for the Computer, Speech and Language article: "Acoustic Adaptation to Dynamic Background Conditions with Asynchronous Transformations" http://dx.doi.org/10.1016/j.csl.2016.06.008.
The files in the zip file are of three types:
- .ctm, which correspond to the output of the automatic speech recognition system and the columns include segment information as well as transcripts of the recognition.
- .sys, which correspond to scoring of the automatic speech recognition system and includes the overall word error rate as well as the number of insertions, deletions and substitutions of the overall system.
- .lur, which provides a more detailed decomposition of the word error rate across different tags.
The following is a description about the naming convention of the files:
TableX-LineY: This is the recognition and scoring output corresponding to Line Y of Table X in the article.
Figure X-BarY: This is the recognition and scoring output corresponding to Bar Y (starting on the left hand side) of Figure X in the article.
All three file types are standard outputs that are recognised by the automatic speech recognition community and can be opened using any text editor.