skills.rest
xjtulyc
xjtulycCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

phonetics-praat

Extract pitch, formants, intensity, spectrograms, and VOT from speech audio.

33|6|Updated Mar 17, 2026
Search Tags:#speech analysis#acoustic phonetics#formant extraction#pitch contour#voice onset time#praat parselmouth#vowel space
One-click install
npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill phonetics-praat
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: phonetics-praat
Source: https://github.com/xjtulyc/awesome-rosetta-skills/tree/main/skills/12-linguistics/phonetics-praat
Command: npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill phonetics-praat

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires praat-parselmouth, numpy, scipy, librosa, matplotlib, pandas.

What problem does it solve?

This Skill helps you turn raw speech audio into measurable acoustic-phonetics signals such as pitch (F0), vowel formants (F1–F3), intensity, spectrogram features, and Voice Onset Time (VOT) for phonological and linguistic analysis.

Core Features & Use Cases

  • Praat-style pitch (F0) extraction: Compute a time-aligned F0 contour and handle unvoiced frames for prosody and intonation studies.
  • Formant analysis for vowel space: Estimate F1/F2/F3 using Praat’s Burg LPC method and visualize vowel quadrilaterals (e.g., comparing vowel categories across speakers).
  • VOT measurement: Estimate the stop consonant burst and voicing onset gap to classify voiced vs. voiceless stop contrasts across languages (with a demo-oriented detection approach).
  • Spectrogram and intensity contours: Generate spectrograms and intensity trajectories to support qualitative and quantitative comparisons (e.g., MFCC exploration, speech rhythm).

Quick Start

Ask the AI agent to load your WAV file and extract F0, F1–F3 at a target time point, generate a spectrogram with intensity, and report VOT and summary statistics for the segment.

Frequently Asked Questions about phonetics-praat

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract pitch and formants from a WAV file for acoustic phonetics analysis?▼

To extract pitch and formants for acoustic phonetics analysis, load your WAV file and request F0 contours and F1-F3 estimation. The Skill uses Praat's Burg LPC method via parselmouth to compute time-aligned features and visualize vowel space.

Can I measure Voice Onset Time and stop consonant voicing contrasts in Python?▼

You can measure Voice Onset Time (VOT) in Python to classify stop consonant voicing contrasts. The Skill estimates the burst onset and voicing gap to differentiate voiced and voiceless stops across languages using a detection-oriented approach.

Do I need Praat and parselmouth installed to compute vowel space and spectrograms?▼

Yes, you need Praat via parselmouth plus numpy, scipy, librosa, matplotlib, and pandas installed in your Python environment. These dependencies are required to reliably compute formants, generate spectrograms, and visualize vowel space quadrilaterals.

What is the best way to visualize vowel space quadrilaterals across different speakers?▼

The best way to visualize vowel space quadrilaterals is by extracting F1 and F2 formants using Praat's Burg LPC method. This Skill computes the formant estimates and plots the vowel categories to facilitate cross-speaker and dialect comparisons.

How do I generate spectrograms and intensity contours for prosody and tone studies?▼

To generate spectrograms and intensity contours for prosody studies, provide your speech audio to the Skill. It computes intensity trajectories and time-aligned spectrograms to support both qualitative exploration and quantitative speech rhythm comparisons.

Why does Praat pitch extraction handle unvoiced frames differently for intonation analysis?▼

Praat pitch extraction handles unvoiced frames differently to prevent false F0 estimates during silence or voiceless segments. This ensures accurate prosody and intonation contours by properly managing time-aligned F0 trajectories across the audio.

Related Skills

Explore More Education & Research Skills→
Zedit42Zedit42

voice-cloning

Generate local speech audio and cloned voices as WAV files.

Community
Intermediate
AbhinavbwjAbhinavbwj
277

acoustic-design

Calculate sound insulation and reverberation time for building acoustic design.

Community
Intermediate
taracodlabstaracodlabs
779

songsee

Generate mel spectrogram, chromagram, and MFCC plots from audio files.

Official
Intermediate
secondskysecondsky
204

ml-model-training

Train machine learning models with scikit-learn, PyTorch, and TensorFlow.

Community
Advanced