This work contains a pipeline used for diarizing audio files with two speakers used in a psychological and paralinguistic research project.
R scripts for the procedure of seperating two speakers in a wave audio file. The work is based on unsupervised hierachical clustering of the Bayesian information criterion (BIC) using MFCC speech features.
To extract the MFCC and Pitch features and audio parts the R package "PraatR" is used by Albin(2014).
Ref: Albin, A. (2014). PraatR: An architecture for controlling the phonetics software "Praat" with the R programming language. Journal of the Acoustical Society of America, 135(4), 2198.