![]() ![]() We focus on a context in which basic linguistic units–such as phonemes–are extracted and robustly classified by humans and other animals from complex acoustic streams in speech data. However, less attention has been given to psycholinguistic data and neurophysiological features recently found in cortical tissue. Many computational theories have been developed to improve artificial phonetic classification performance from linguistic auditory streams. We also include Strong and Weak scaling tests of our implementation on HPC resources and an appendix including a battery of complementary experiments showing the classification accuracy levels of different instances of the EL in the CSTM. An appendix including the Computational Setup of our CSTM, which describes its object oriented inheritance structure as well as the parallelization strategy used for its implementation in HPC resources is provided in. ![]() ![]() A GitHub repository with the code used to implement the CSTM as well as the scripts to generate the datasets used in this work is available from. This folder includes a set of 840 corpora which are distributed in 2 corpora for each configuration organized by 2 sets of synthesized voices, 3 syllabic conditions and 10 vocabularies all distributed in 6 acoustic variants, beyond the original version of the corpora. A folder containing all the datasets (audio file corpora) employed in the present research to train the EL and the SVM and to test the complete CSTM is provided in. A spreadsheet file that includes numerical results returned by a complementary set of experiments is provided at. Associated Data Data Availability StatementĪll the data in this work are available from Zenodo ( ) A spreadsheet file that includes all the numerical results returned by the experiments as well as the complete Statistical Significance tests conducted in this work is provided at. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |