phonetics-praat

Community

Extract pitch, formants, and VOT in Python.

Authorxjtulyc
Version1.0.0
Installs0

System Documentation

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.

Dependency Matrix

Required Modules

praat-parselmouthnumpyscipylibrosamatplotlibpandas

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: phonetics-praat
Download link: https://github.com/xjtulyc/awesome-rosetta-skills/archive/main.zip#phonetics-praat

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.