MFCC Feature Extraction Pipeline

Spoken Language Technologies Course Assignment

For this course assignment, I implemented a Mel-Frequency Cepstral Coefficients (MFCC) extraction pipeline. Given an input speech signal, I implemented all of the steps using only the numpy and scipy Python libraries. The output of the assignment was a Jupyter notebook with the implementation, as well as some plots to visualize the MFCCs.

(I won’t share the code/implementation details publicly for purposes of academic integrity)