FEATURES OF PRAAT

NAME- Tanvii Shanker

ROLL NO.- 1050

SEMESTER- 2nd

SUBJECT- Linguistics

Summitted to- Mr. Chander Shekhar

Singh
 ACKNOWLEDGEMENT
I would like to express my gratitude and
thankfulness to my teacher Mr. Chander
Shekhar Singh who gave me this
opportunity to complete such
knowledgeable project of Linguistics.
I came to know about the project PRAAT
and its features from this project, all
thanks to my teacher.

NAME- Tanvii Shanker

ROLL NO.- 1050
 PRAAT
Praat is scientific tool for those studying
linguistics that can analyse spectrograms.
Praat can read sounds recorded with the program
or audio files recorded in another way. Once
loaded, Praat generates a graph of waves which
indicate intonation, intensity, volume and other
complex details.
Praat is able to isolate certain sound bites or filter
frequencies either manually or using scripts.
There's no avoiding that Praat is a useful tool for
linguists. It's difficult to get to grips with, though,
and although there is an extensive manual, it's
aimed mainly at linguistic experts. For those
seeking an introduction to audio analysis and
spectrographs, they may well find Praat too
complex but Praat is a powerful audio analysis
tool that will give linguists a high degree of control
over spectrographs.
Praat is a freeware program for analysis and
reconstruction of acoustic speech signals. It offers
a wide range of standards and non-standard
procedures including spectrographic analysis,
articulatory synthesis and neutral networks.
PRAAT is a computer program for analysing,
synthesizing, and manipulating speech. It has been
developed since 1992 by Paul Boersma and David
Weenink at the Institute of Phonetic Sciences of
the University of Amsterdam. There are versions
for most of the common operating systems:
Macintosh, Windows, Linux, and several Unix
workstations (Solaris, Silicon Graphics, Hewlett-
Packard). By September 2001, there were more
than 5,000 registered users in 99 countries.
The introduction of the computer has brought
about a virtual revolution in the linguistic sciences
with respect to the usage of speech recordings. A
lab full of cumbersome machinery has now been
replaced by one PC, Mac or workstation, on which
anyone who puts his mind to it can record,
annotate and modify speech with some simple
commands or a few mouse clicks. Even the
calculation of some speech parameters that were
rather complicated to obtain in the past (like pitch
and spectral analysis) but frequently used in
phonetic research nonetheless, are now often just
one or two mouse clicks away. As a result, a
growing number of colleagues use for with speech
sounds in their linguistic explorations.

WHY PRAAT?
You will want to choose PRAAT for most of your
phonetic research not only because it is the most
complete program available or because it is
distributed for free, but also because it comes with
the algorithms. The pitch analysis algorithm is the
most accurate in the world; the articulatory
synthesis is the only one that can handle dynamic
length changes (ejectives), non-glottal myo-
eleastics (trills), and sucking effects (clicks,
implosives); and the gradual learning algorithm is
the only linguistically-oriented learning algorithm
that can handle free variation. But of course, there
will always be things related to phonetics that
other programs are better at. Hence, for everyone’s
convenience, PRAAT has therefore been designed
to interface reasonably well with Matlab, SPSS,
Excel, and the Klatt synthesizer.

PRAAT is probably the most comprehensive

toolbox for phonetic research available worldwide,
and it is certainly the most affordable; it actually
costs no money at all. PRAAT rejuvenates at an
alarming rate. PRAAT started out as a collection of
programs that were specifically designed to
produce top-quality graphic representations of
speech, i.e. oscillograms, spectra, spectrograms,
fundamental frequency and intensity plots, etc.
However, the flexible and well-planned structure of
the program allowed its maker(s) to extend
PRAAT's functionality almost indefinitely. Often,
the same tasks can be done by PRAAT using
different modules with different algorithms. Pitch
extraction, for example, can be done with the aid
of atleast four different algorithms:
autocorrelation, cross-correlation, SPINET, and
subharmonic summation. Helpers are available for
each of the algorithms, explaining the meaning of
the many parameter values that can be specified in
for each algorithm and providing references to the
literature. Each algorithm comes with a set of
default parameter settings that can be over-ridden
by the user. Also, there is an unmarked algorithm
(which turns out to be an autocorrelation
technique) that allows no special tuning. In all,
there would seem to very little that PRAAT cannot
do for you. However, some things can be done
instantaneously, other tasks can be performed
only in non-obvious ways that the novice user will
never discover by himself. It should be pointed out
that PRAAT is not a self-study course in
experimental/instrumental phonetics. To be true, a
detailed on-line technical reference manual is
included with the program, but it generally does
not discuss the pros and cons of alternative
approaches/solutions to speech analysis
problems. The user must decide on his own which
algorithm will suit his purposes best.

Multi-panel Editors
A recent development seems to have been toward
providing smorgasbord-like complex presentations
which display speech parameters as a function of
time in multiple synchronized panels. Two such
complex editors are provided.
1. The first is the basic waveform editor (which
is invoked by a Sound object), which can be
tailored to the user's taste. It allows for
simultaneous display of the waveform,
spectrogram, formant tracks (in red), a pitch
curve (blue) and an intensity curve (yellow), all
superimposed on the spectrogram. Each of
the displays can be switched on/off, scales
can be adjusted for optimal visual resolution,
there is a (limited) choice of algorithms that
can be invoked for each display, and
parameter settings can be chosen. Values can
be eyeballed and read out under cursor
control; digital readouts can be obtained
through data queries. The edit functions allow
cut, copy and paste, zero, and time-reverse.
The parameter tracks can be extracted from
each display and stored separately.
2. The second is the editor that is used for
Manipulation objects. The waveform is
displayed together with a pitch track (default
pitch determination algorithm) and a relative
duration parameter. In the waveform the
moments of glottal closure are indicated by
vertical blue lines. The corresponding pitch-
synchronous frequency value is displayed in
light grey in the pitch manipulation display.
Presence/absence and location of glottal
pulses can be manipulated. Also the user can
stylize the pitch curve and/or change the pitch
curve in any way he wants. Similarly, time
intervals can be selected and given different
relative durations. This allows portions of the
utterance to be stretched or compressed in
time. After manipulation the sound can be
resynthesized using two different analysis-
resynthesis schemes:
a. PSOLA resynthesis: a relatively simple
waveform manipulation technique that
affords the manipulation of pitch and duration
but detracts very little from the original sound
quality.
b. LPC resynthesis: a statistical data
reduction technique that generally leads to
considerable loss of sound quality but affords
± in principle ± the manipulation not only of
prosodic parameters (pitch and duration) but
also of spectral parameters (sound quality or
timbre).

Additional displays
 Cochleagrams. Hidden further down the
hierarchy of PRAAT functions are the
possibilities to create auditory spectrograms
(or cochleagrams). As an option with the
cochleagram the loudness (expressed in
Sones) of a time-slice can be queried
Vowel diagrams. It is also possible to plot
a vowel, or even a series of vowels, as points
in a vowel diagram, i.e. a two-dimensional
graph plotting the first formant frequency F1
against the second formant frequency F2.
Optionally, dispersion ellipses can be drawn
around the scatter clouds of vowel points in
the F1-by-F2 display. Such plotting facilities
are also provided by the ± expensive ± Kay
Computerized Speech Lab (CSL) package.
Using the annotation tools incorporated in
PRAAT, beautiful print-quality vowel diagrams
can be produced. The display could also be
used as part of a user interface to generate
vowel sounds by moving the cursor around in
the display using LPC synthesis.

Scripting language
PRAAT comes with a full programming
language which can be used to create script
that can be run in batch mode, allowing the
user to analyse large quantities of data
automatically ± with or without user
intervention, and to store measurements in a
database for off-line statistical data analysis
using such packages as SPSS. PRAAT scripts
can be programmed from scratch or the user
can build upon a basic script that is generated
by the PRAAT macro-recorder. PRAAT keeps a
log of any button pressed or keystroke
entered during the interactive session. At any
moment the session's history can be loaded
into a text editor and used as a starting point
for a program. Using the programming tool,
the user can extend PRAAT any way he likes,
defining new functions and making these
easily accessible in the PRAAT user interface
as optional buttons. Any user with a basic
grasp of computer programming will be able
to construct PRAAT scripts. The PRAAT
interactive manual provides lots of sample
scripts to give the novice a basic feel of how
to go about generating scripts.
PRAAT as a sound generator
For the teaching of basic acoustics ± often a tough
subject for undergraduate language students with
a non-technical background ± PRAAT provides a
complex tone generator with very limited
possibilities.
PRAAT also allows the user to define any
waveform by typing in and/or editing full formulae.
Therefore, it would be ideal if some pre-stored or
external sound (either from a tape recording of
from a live microphone) could be simultaneously
displayed in an on-line fashion as a waveform and
as a spectrum.

Functionality
The following gives you an idea of the features of
the PRAAT program-

1. Speech analysis:
 spectral analysis (spectrograms)
 pitch analysis
 formant analysis
 intensity analysis
 jitter, shimmer, voice breaks
 cochleagram
 excitation pattern

1. Speech synthesis:
 from pitch, formant, and intensity
 articulatory synthesis
 Klatt acoustic synthesis

1. Labelling and segmentation:

 label intervals and time points on multiple tiers
 use phonetic alphabet
 use sound files up to 2 gigabytes (3 hours)

1. Speech manipulation:
 change pitch and duration contours
 filtering
1. Listening experiments:
 identification and discrimination tests

1. Graphics:
 high quality for your articles and thesis
 produce Encapsulated PostScript files
 integrated mathematical and phonetic
symbols

1. Statistics:
 multidimensional scaling
 principal component analysis
 discriminant analysis

1. Programmability:
 easy programmable scripting language
 communicate with other programs
 create hypertext manuals with sound I/O
 HOW TO RECORD SPEECH
IN PRAAT?

To record a speech sound into Praat, you need a

computer with a microphone.
To record from the microphone, perform the
following steps:
1. Choose Record mono Sound... from the New
menu in the Object window. A Sound
Recorder window will appear on your screen.
2. On the left in the Sound Recorder window,
choose the appropriate input device, e.g.
choose Internal microphone. (On Windows,
instead right-click the loudspeaker symbol in the
Start bar; see Sound Recorder for more details.)
3. Use the Record and Stop buttons to record a
few seconds of your speech.
4. Use the Play button to hear what you have
recorded.
5. Repeat steps 3 and 4 until you are satisfied with
your recording.
6. Click the Save to list button. Your recording will
now appear in the Object window, where it will be
called "Sound sound".
7. You can now close the SoundRecorder window.
8. When you saved your sound to the Object
window, some buttons appeared in that window.
These buttons show you what you can do with the
sound. Try the Play and View & Edit buttons.

SPEECH SIGNAL ANALYSIS

USING PRAAT

Speech plays the most important role during

verbal communication between humans. And
phonetics is the study and classification of speech
sounds.
It is basically categorised into the following three
groups:
1. Articulatory phonetics deals with speech
production and how sound is produced.

2. Auditory phonetics deals with speech

perception, and how sound is perceived.

3. Acoustic phonetics deals with the study of

properties of the speech wave.
This process is termed the speech chain or the
speech communication pathway.

An introduction to speech processing

Analysis of speech signals is an important task. It

deals with the manipulation of sound signals to
extract meaningful information from them. There
are many techniques for speech processing.
Speech, being a non-stationary signal,
continuously keeps on changing; hence, in order to
model the speech signal, we follow the strategy of
segmentation, which is the process of assuming
the speech wave to be a static signal for a short
period of time in which it remains almost constant.
The typical length of such intervals is 20ms to
30ms. Hence, a speech signal is segmented into
frames of 20ms-30ms, and each frame is analysed
separately.

Spectrun Analysis

Normally, the signal is represented in the time

domain, where the horizontal axis represents time
and the vertical axis represents the amplitude
(loudness) of the speech signal. The difficulty with
the time domain is that it can provide only a
limited amount of information about the signal.
Fourier analysis is an important process, which
transforms the signal from the time domain to the
frequency domain, also referred to as the Fourier
domain. The frequency domain represents the
signal in amplitude frequency (Hertz) dimensions.
The signal representation in the frequency domain
is also known as the frequency spectrum, or just
the spectrum of the signal.
Spectrogram Analysis

Spectrogram analysis is widely used in vowel

identification, silence detection or formant
analysis from specific speech utterances. Further,
a spectrogram can also be used to identify the
category or class of sounds (such as nasals,
plosives, fricatives, etc).

Formant Analysis

A formant can be considered as a resonance of

the vocal tract. In a typical spectrum envelope of a
speech signal, formants depict picks of the
envelope. Most of the vowels are characterised by
the first two formants (F1 and F2) only. This is
because formant frequencies reflect the
articulatory gestures related to vowel height and
the front-back position.
Format analysis is widely used in linguistics. There
are many techniques to extract formants from a
given speech signal. 
 CONCLUSION

In English, a language with free lexical stress,

words have different stress patterns. The stress
placement of a word can be detected with the
auditory and the acoustic method. In order to
investigate words or utterances with the acoustic
method, the speech analysis software Praat  can
be used. With the help of Praat, words and
utterances can be recorded and subsequently
analysed. The duration of a syllable or vowel can
be measured as well as the intensity, the pitch
height or the formants.
In summary, PRAAT is a formidable research and
teaching tool for phonetics.

BIBLOGRAPHY

 www.uni-bamberg.de (conclusion)
 SpeakUspeak Article
 Wikipedia
 https://www.fon.hum.uva.nl/praat/
 PRAAT Tutorial- Stanford University
 https://www.ee.iitb.ac.in/student/~daplab
/resources/SpeechAnalysisUsingPRAAT.p
df