Featured Linguist!

Jost Gippert: Our Featured Linguist!

"Buenos dias", "buenas noches" -- this was the first words in a foreign language I heard in my life, as a three-year old boy growing up in developing post-war Western Germany, where the first gastarbeiters had arrived from Spain. Fascinated by the strange sounds, I tried to get to know some more languages, the only opportunity being TV courses of English and French -- there was no foreign language education for pre-teen school children in Germany yet in those days. Read more



Donate Now | Visit the Fund Drive Homepage

Amount Raised:

$34378

Still Needed:

$40622

Can anyone overtake Syntax in the Subfield Challenge ?

Grad School Challenge Leader: University of Washington


Publishing Partner: Cambridge University Press CUP Extra Publisher Login
amazon logo
More Info

Software Details

Title: Prosody Research Tools Available
Submitter: Yi Xu
Description: We are pleased to announce the availability of two Praat script tools for
conducting large-scale prosody research: PENTAtrainer and ProsodyPro, both
freely accessible at http://www.phon.ucl.ac.uk/home/yi/tools.html.

1. PENTAtrainer (http://www.phon.ucl.ac.uk/home/yi/PENTAtrainer/)

An interactive script for automatic extraction of pitch targets for prosody
synthesis. It is based on the qTA implementation of the PENTA model, and it
allows users to:

- Automatically extract pitch target parameters (slope, height, strength)
- Resynthesize F0 contours based on the extracted parameters
- Specify target location and restrict direction of target slope
- Exhaustively process all wave files in a folder
- Perform the same f0 analyses as ProsodyPro (See below)
- Automatically collect extracted parameters from all sounds in a folder
and save them in ensemble files for ease of further analysis and processing


2. ProsodyPro (http://www.phon.ucl.ac.uk/home/yi/ProsodyPro/)

An interactive script for large-scale systematic prosody analysis. This is
an updated version of its predecessor TimeNormalizeF0. Among its many
feature are the following:

- Semi-automatic extraction of F0 contours, allowing users to improve the
accuracy of F0 tracking by rectifying vocal pulse marking
- Exhaustively process all wave files in a folder
- Automatically save time-normalized F0 and intensity contours for selected
intervals
- Automatically save continuous F0 velocity contours for selected intervals
- Automatically save many prosodic measurements, including: maxf0, minf0,
f0range, meanf0, mean intensity, duration, max velocity, final velocity,
final f0 and mean intensity
- Automatically collect extracted contours and measurements from all sounds
in a folder and save them in ensemble files for ease of further analysis
and processing

Explanations and instructions can be found at the web sites. For more
information and bug reports, please contact yi.xu@ucl.ac.uk
Linguistic Field(s): Computational Linguistics
Phonetics
Phonology
Text/Corpus Linguistics
Cognitive Science

LL Issue: 21.3735
Date Posted: 21-Sep-2010

Search Again

Back to Software Index