Oralstats Aroca is a tool designed to simplify the process of querying and downloading data from speech corpora. It has been designed originally to provide researchers with the ability to query and download data from the Ameresco Speech Oral Corpus (available at www.corpusameresco.com) as well as personal corpora. With a highly extensible and customizable SQL database backend, you can use Oralstats Aroca to create reference material from your transcripts; and with the generated data you can also use the Oralstats module in its core version. Basically, Oralstats Aroca offers an efficient and user-friendly experience for researchers.
You can see the script in action using the Ameresco Corpus at the following link:
https://adrin-cabedo.shinyapps.io/aroca_viewer/
If you use Oralstats Aroca in your research, please cite the following publication:
Cabedo, A. & Carcelén, A. (2021). Oralstats Aroca. Version beta 1.2. Available online at https://github.com/acabedo/aroca
A tutorial covering the basic usage of Oralstats Aroca is available at https://github.com/acabedo/aroca/tree/main/tutorial. Additionally, a video demonstrating the transformation module of Oralstats on a sample from the Ameresco corpus can be found at https://youtu.be/KWzvIrh-980.
To use Oralstats Aroca with your own corpus, you should have the following:
-
Basic knowledge of R (specifically Shiny)
-
Basic knowledge of SQL language
-
A SQL database (e.g. PostgreSQL, SQlite, MySQL)
-
(Optional but recommended) Data processed and converted using the Oralstats transformation module. The creacion.zip file [https://github.com/acabedo/aroca/blob/main/creacion.zip] can be downloaded and the oralstats_creacion.app file executed for this purpose. Sample files are included in the txt, pitch, and intensity folders for use as examples. You can see it working at https://youtu.be/KWzvIrh-980.
If you have any questions or suggestions, please feel free to contact us at: adrian.cabedo@uv.es / andrea.carcelen@uv.es
GNU General Public License v3.0 Permissions of this strong copyleft license are conditioned on making available complete source code of licensed works and modifications, which include larger works using a licensed work, under the same license. Copyright and license notices must be preserved. Contributors provide an express grant of patent rights.