Skip to content

szekrenyesi/prosotool

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ProsoTool (emPros)

ProsoTool is a language independent algorithm implemented as a Praat script for the automatic annotation of intonation. The script stylizes F0 contour into larger (perceptually relevant) intonation segments which are classified based on the individual speech properties of the speakers. This tool is also integrated into the e-magyar language processing system.

Requirements

  • Praat 6.0.13 or later

Input

  • The speech sound file in WAV format (sample.wav)
  • The acoustic annotation of speaker change in Praat TextGrid format (sample.TextGrid). The speakers must be represented in different tiers.

Output

  • Format: Praat TextGrid
  • The results are separated for every speaker
  • F0Mov: The type of intonation movements (rise, fall, descending, ascending, level)
  • F0Level: The relative position of movements (as point to point vector) in the individual vocal range of the speaker
  • F0Value: The above information expressed in Hertz

Usage

Praat prosotool.praat <INPUT> <STYLIZATION> <SMOOTHING> <PITCH_EXTRACTION> <OPERATING_SYSTEM> 

Options

  • INPUT: The path of input directory
  • STYLIZATION: The scale of stilization in semitones (integer number). The langer number results stronger stylization.
  • SMOOTHING: The scale of smoothing (real number). The smaller number results stronger smoothing.
  • PITCH_EXTRACTION: The method of pitch extraction: "standard" (with fixed parameters) or "dynamic" (speaker-dependent)
  • OPERATING_SYSTEM: The type of running environment: "windows" or "unix"

Example

./Praat prosotool.praat input 2 1.5 dynamic unix

Citation

Please, cite this article on ProsoTool and here is the way how to cite Praat.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages