This tutorial will explore extracting audio features from a WAV file or set of WAV files and preparing them for NLP and machine learning tasks.

These files relate to a live-coding demonstration given at the UW Phonetics Lab in November of 2018. The script measure-formants-automated.praat was the focus of the demonstration.

Voice onset time (VOT) is an acoustic property of stop consonants that is commonly manipulated in studies of phonetic perception. This paper contains a thorough description of the "progressive cutback ...