CNN-based audio segmentation toolkit. Allows to detect speech, music, noise and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.
Read, write, and manipulate Praat TextGrid files with Python
SpeCT - Speech Corpus Toolkit for Praat. Documentation: https://lennes.github.io/spect/
Praat TextGrid Objects in R
A Praat script for creation of pictures (waveform, spectrogram, pitch contour, aligned with a textgrid). It creates figures in PNG PDF wmf eps, PraatPic, of all the Sound and TextGrid files it finds in a folder. The pictures contain a waveform (optional), a spectrogram(optional), the F0 track optional and a the content of the tiers of the TextGr...
Record, concatenate and synchronize Twitch live streams and remove background music
Gentle and praatio scripts for easy forced alignment
A small wrapper package around whisper-timestamped. Create force-aligned transcription TextGrids from raw audio!
A Whisper to TextGrid script that I use to automatize Corpus Annotation on Praat, with speaker diarization.
A set of Praat scripts to analyze vowels: 1) extracting data (F0, F1, F2, F3, F4, interval duration (ms) and intensity (dB)) and 2) extracting whole formant data. Scripts for extracting data from point tiers are also avaliable
Praat script written to analyze EGG signals; materials for ASA submission.
A utility to find the best audio matches for videos and sync them together, perhaps for your films
Mahr, et al. (2015). Anticipatory coarticulation facilitates word recognition in toddlers.
Praanscribe is an open-source Python CLI application designed to automate the segmentation of parts of speech and the annotation of sounds, as much as possible, using Praat.
Add a description, image, and links to the praat topic page so that developers can more easily learn about it.
To associate your repository with the praat topic, visit your repo's landing page and select "manage topics."