PRAAT PROSODIC FEATURE
EXTRACTION TOOL
Instructor:Dr.Veton Kepuska
Student:Dileep Narayan.Koneru
INTRODUCTION
• There has been an increasing interest in utilizing a wide variety of
knowledge sources in order to perform automatic tagging of
speech events, such as sentence boundaries and dialogue acts.
• In addition to the word spoken, the prosodic content of the
speech has been proved quite valuable in a variety of spoken
language processing tasks such as sentence segmentation and
tagging, dis_uency detection, dialog act segmentation and
tagging, and speaker recognition.
• Here in this project I used an open source prosodic tool for
extracting the prosodic analysis.This tool uses praat for its
implementation.
FEATURES
 Duration Features
 F0 Fetures
 Range Features
 Movement Features
 Slope Features
 Energy Features
IMPLEMENTATION
 Statistical Feature Computation
 1. Run Praat
 2. Open stats batch.praat from Read\Read from file" on the
menu of Praat Objects.
 3. Click \Run\Run" on the menu of ScriptEditor.
• 4. Enter parameters. Type ..\demo-wavinfo list.txt and
..\demo\work dir in the two
boxes, and then check
\yes" in the radio box.
• 5. Click \OK" to start processing with the con_gurations or
\Cancel" to close the interface. Clicking the \Apply"
button (if available) also starts processing but it keeps the
interface on after the work is done. The \Standards" button
(if available) gives the option to restore the default
con_gurations.
• 6. Process related information is displayed in the Praat Info
Window.After computation is complete, the statistics _les
can be found at ../demo/work dir/stats files.
• Prosodic Feature Extraction
• This is also done in the same way as statistical feature
computation.
• But the main difference is the file main_batch is run instead
of stats_batch file
The requirements needed for the
tool and its basic elements are:

Procedures to obtain the basic elements that are directly needed for prosodic feature extraction.The grayed
ovals represent operations implemented in the tool, while the grayed rectangles represent the basic
elements. Note that Forced Alignment is not a part of the tool, and so it appears in white
The use of basic elements for
various feature calculations:
 After the statistic feature calculation we get param files from
witch we can view the pitch,raw pitch,stylised
pitch,intensity,energy etc
 From those I presented here the pitch and its informationand
the prosodic features table and its information
Pitch tier
 From this we can get the pitch information
Pitch information
Stylized pitch
 From this we can get the stylized pitch information
Stylized pitch info
Prosodic features table
Prosodic feature table info
RESULT AND COCLUSION
 Hence the prosodic features of the speech file demo_c.wav
are extracted given its word and phone alignment.
 This prosodic model when combined along with a language
model can form an event detection system
REFERENCES
 www.google.com
 An Open Source Prosodic Feature Extraction Tool
Zhongqiang Huang, Lei Chen, Mary Harper