interspeech16-ng.tar.gz (297 kB)

Interspeech 2016 - Experiment results for the paper "Combining weak tokenisers for phonotactic language recognition in a resource-constrained setting"

Download (297 kB)
dataset
posted on 27.06.2016, 13:17 by Wai Man Ng, Bhusan Chettri, Thomas Hain
This dataset contains the test results for the experiments described in the interspeech 2016 paper "Combining weak tokenisers for phonotactic language recognition in a resource-constrained setting" DOI: 10.21437/Interspeech.2016-630.

The folders are organised in TABLE_2 / TABLE_3 and TABLE_4. In each folder, there are multiple *.detectionscore.DCF files. They are the scoring results based on different experimental conditions.

In the top directory, three csh scripts
gen_TABLE_2_results.csh
gen_TABLE_3_results.csh
gen_TABLE_4_results.csh
are included. When executed, it will automatically extract the relevant scores from the folder and displays the language recognition results as described in the paper.


Funding

EPSRC Programme Grant EP/I031022/1 (Natural Speech Technology)

History

Ethics

There is no personal data or any that requires ethical approval

Policy

The data complies with the institution and funders' policies on access and sharing

Sharing and access restrictions

The data can be shared openly

Data description

  • The file formats are open or commonly used

Methodology, headings and units

  • Headings and units are explained in the files

Licence

Exports