A suite of vowel formant
extraction tools tailored to research questions in
Dartmouth Linguistic Automation
Completely Automated Vowel Extraction
Audio → Formants
This automated method is designed for "big data" research projects where a general vowel space is prioritized over word-level transcription accuracy.
Semi-Automated Alignment and Extraction
Audio + Transcriptions → Formants
Equivalent to the FAVE pipeline, with additional input and output options. Designed for research goals that require very accurate transcriptions.
Our system makes use of automatic speech recognition (through our research software as well as YouTube's closed captioning), FAVE-Extract, ProsodyLab-Aligner, and the R Vowels package to automate vowel analysis for sociophonetics.