Phonetics Lab Software
This page houses guides for the software installed on lab computers and other software used by lab members.
Ardour is the digital audio recording and processing software we're now using in conjunction with the 8-channel audio interface, in place of Sound Studio.
Git & Subversion
Software versioning and revision control systems useable by UW linguistics students. See the UW Treehouse Wiki for more information.
Can be found on Github
Montreal Forced Aligner
Easy installation includes downloading Miniconda and using a conda environment already populated with software. Note that pre-trained G2P (Grapheme-to-Phoneme) models may not output standardized IPA nor X-SAMPA, and the author/contact himself has personally recommended to use other G2P models like Epitran.
A comparison of the various forced-aligners available can be found here
Praat is a free computer software package for the scientific analysis of speech in phonetics. It was designed, and continues to be developed, by Paul Boersma and David Weenink of the University of Amsterdam.
You can download Praat here .
The following is a file to help you get started in Praat File:OpeningPraat.pdf
Introduction to PyschoPy (by Katie Drager, hosted with permission). File:PsychoPy handout.pdf
Hugo Quené has a nice PDF tutorial that starts with the basics but also covers many popular analysis techniques.
Manipulate Praat files and use Praat functions directly from R. (Tip: check out tg.boundaryMagnet() for a useful helper function when working with TextGrids)
Web interface for accessing the Microsoft Speech API maintained by the UW Sociolinguistics Lab. Produces machine-generated transcriptions with timestamps. Also available as a desktop app for MacOS.
"ELAN is a professional tool for the creation of complex annotations on video and audio resources." Hosted by the Max Planck Institute for Psycholinguistics. Useful for fast and streamlined transcription and correction of transcriptions.