Module: 1

Introduction
Sumana Chatterjee
Department of Biomedical Engineering
Netaji Subhash Engineering College
 Concept of Discrete Time Signal

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 2

 Concept of Discrete Time Signal

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 3

 Sampling

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 4

 Sampling Rate

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 5

 Nyquist Rate

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 6

 Sampling Theorem

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 7

 Sampling Theorem

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 8

 Sampling Theorem

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 9

 Sampling Theorem

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 10

 Sampling Theorem

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 11

 Reconstruction of Signal

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 12

 Reconstruction of Signal

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 13

 Convolution
• Convolution is a mathematical way of combining two signals to form
a third signal.
• It is the single most important technique in Digital Signal Processing.
• Using the strategy of impulse decomposition, systems are described
by a signal called the impulse response.
• The convolution of two signals in the time domain is equivalent to the
multiplication of their representation in frequency domain.
• Mathematically, we can write the convolution of two signals as
y(t)=x1(t)∗x2(t)=∫∞−∞x1(p).x2(t−p)dp

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 14

 Steps for convolution
• Take signal x1(t) and put t = p there so that it will be x1(p).
• Take the signal x2(t) and do the step 1 and make it x2(p).
• Make the folding of the signal i.e. x2(−p).
• Do the time shifting of the above signal x2[-p−t]
• Then do the multiplication of both the signals. i.e. x1(p).x2[−(p−t)]

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 15

 Example
• Let us do the convolution of a step signal u(t) with its own kind.
y(t)=u(t)∗u(t)=∫∞−∞[u(p).u[−(p−t)]dp
• Now this t can be greater than or less than zero, which are shown in below figures

So, with the above case, the result arises with following possibilities
y(t)={0, for t<0
∫t0 1dt, for t>0
={0, for t<0
t, for t>0=r(t)

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 16

 Properties of Convolution
1. Commutative:
It states that order of convolution does not matter, which can be shown
mathematically as x1(t)∗x2(t)=x2(t)∗x1(t)
2. Associative
It states that order of convolution involving three signals, can be anything.
Mathematically, it can be shown as x1(t)∗[x2(t)∗x3(t)]=[x1(t)∗x2(t)]∗x3(t)
3. Distributive
Two signals can be added first, and then their convolution can be made to
the third signal. This is equivalent to convolution of two signals individually
with the third signal and added finally. Mathematically, this can be written
as x1(t)∗[x2(t)+x3(t)]=[x1(t)∗x2(t)+x1(t)∗x3(t)]

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 17

 Convolution
• Area: If a signal is the result of convolution of two signals then the area of
the signal is the multiplication of those individual signals. Mathematically
this can be written If y(t)=x1∗x2(t), Then, Area of y(t) = Area of x1(t) X Area
of x2(t)
• Scaling: If two signals are scaled to some unknown constant “a” and
convolution is done then resultant signal will also be convoluted to same
constant “a” and will be divided by that quantity as shown below.
If, x1(t)∗x2(t)=y(t), Then, x1(at)∗x2(at)=y(at)/a,a≠0
• Delay: Suppose a signal y(t) is a result from the convolution of two signals
x1(t) and x2(t). If the two signals are delayed by time t1 and t2 respectively,
then the resultant signal y(t) will be delayed by t1+t2. Mathematically, it
can be written as − If, x1(t)∗x2(t)=y(t), Then x1(t−t1)∗x2(t−t2)=y[t−(t1+t2)]
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 18
 Types of Convolution

•Continuous convolution
•Discrete convolution

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 19

 Continuous Convolution

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 20

 Discrete Convolution

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 21

 Properties of Convolution

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 22

 Properties of Convolution

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 23

 Properties of Convolution

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 24

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 25
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 26
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 27
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 28
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 29
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 30
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 31
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 32
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 33
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 34
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 35
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 36
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 37
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 38
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 39
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 40
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 41
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 42
 Correlation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 43

 Auto Correlation Function

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 44

 Auto Correlation Function of Power Signals

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 45

 Properties

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 46

 Density Spectrum

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 47

 Cross-Correlation Function

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 48

 Properties of Cross Correlation Function of Energy
and Power Signals

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 49

 Correlation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 50

 Correlation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 51

 Correlation

•Cross-Correlation
•Auto-Correlation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 52

 Cross-Correlation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 53

 Auto-Correlation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 54

Properties of Auto-Correlation & Cross-Correlation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 55

 Normalized Auto & Cross-Correlation Sequence

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 56

 Compute Auto-Correlation Sequence

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 57

 Cepstral Analysis

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 58

 Cepstral Analysis

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 59

 Cepstral Analysis

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 60

 Simple Signal Conversion System

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 61

 Signal Conversion System

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 62

 A/D Conversion

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 63

 Signal Conversion System

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 64

 D/A Conversion

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 65

 D/A Conversion

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 66

 D/A Conversion

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 67

 D/A Conversion

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 68

 Input Signal Interfacing

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 69

 Current to Voltage Conversion

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 70

 Voltage to Voltage Conversion
• To condition the output voltage from transducer or sensor to the A/D
converter, scaling and shifting operations are necessary. Mathematically,
these operations can be modeled with:

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 71

 Frequency to Voltage Conversion

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 72

 Signal Conversion System
• Signal conversion is a fundamendal process to condition
measurement signal or output signal from one device to another
device for further processing.
• The conversion must be done if the measurement or the output
signal does not meet input specification of the receving device.
• The incompatibility is the reason behind signal conversion.
• As there are many cases where we need to control analog plants with
digital computer, understanding A/D and D/A conversion processes
become an indispensable and fundamental knowledge.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 73

 What is a Frequency Domain?
• The Frequency Domain refers to the analytic space in which mathematical
functions or signals are conveyed in terms of frequency, rather than time.
• For example, where a time-domain graph may display changes over time, a
frequency-domain graph displays how much of the signal is present among
each given frequency band.
• It is possible, however, to convert the information from a time-domain to a
frequency-domain.
• An example of such transformation is a Fourier transform.
• The Fourier transform converts the time function into a set of sine waves
that represent different frequencies.
• The frequency-domain representation of a signal is known as the
"spectrum" of frequency components.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 74

 How does the Frequency Domain work?
• The Frequency domain works by allowing a representation of the qualitative
behavior of a system, as well as characteristics of the way the system response to
changes in bandwidth, gain, phase shift, harmonics, etc.
• A discipline in which the frequency domain is used for graphical representation is
in music.
• Often audio producers and engineers display an audio signal within a frequency
domain in order to better understand the shape and character of an audio signal.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 75

 Applications of Frequency Domain
• For example, auditory sounds exist between a range of 20-20,000Hz, and
some frequencies are harder for the human ear to withstand.
• The frequency 3,400Hz is a harsh frequency (the sound of babies crying),
and the human ear is specifically tuned to respond viscerally to that sound.
• An audio engineer may reduce the strength of that frequency in the
frequency domain using an audio equalizer.
• By displaying the audio signal in the frequency domain, an engineer can
boost and reduce signals to make the sounds more pleasant for the human
ear.
• The Fletcher-Munson curve is a widely used function that lays atop the
frequency domain that audio engineers often reference when mixing
various frequencies.
• The function's curve selectively boosts and reduces frequencies to allow
the audio engineer to raise the gain of the signal while mitigating the
unpleasant sounds.
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 76
 Spectral Analysis
• A continuous or discrete time-series, such as x = x(t) or xn = {x0, x1,. . .}, can be analyzed in
terms of time-domain descriptions and frequency-domain descriptions.
• The latter is also called spectral analysis and reveals some characteristics of a time-series,
which cannot be easily seen from a time-domain description analysis.
• Spectral analysis is used for solving a wide variety of practical problems in engineering
and science, for example, in the study of vibrations, interfacial waves and stability
analysis.
• In spectral analysis, the time-series is decomposed into sine wave components using a
sum of weighted sinusoidal functions called spectral components.
• The weighting function in the decomposition is a density of spectral components or
spectral density function.
• The actual method of decomposing a time-series into a sum of weighted sinusoidal
functions is to use Fourier transform which has both continuous and discrete versions
corresponding to continuous time-series of type x = x(t) and discrete time-series of type
xn = {x0, x1,. . .}, respectively.
• Most recorded time-series data in engineering practice are of discrete type and
numerical calculations of the Fourier transform are usually done using digital computers,
which can only deal with discrete data and therefore use discrete Fourier transform.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 77

 Fourier Transform

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 78

 Fourier Transform

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 79

 Frequency Spectrum

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 80

 Power Spectrum

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 81

 Cross Spectrum

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 82

 Coherence Function

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 83

 Linear Filtering
• In everyday terms, the fact that a filter is linear means simply that the
following two properties hold:
• SCALING: The amplitude of the output is proportional to the amplitude of
the input (the scaling property).
• SUPERPOSITION: When two signals are added together and fed to
the filter, the filter output is the same as if one had put each signal through
the filter separately and then added the outputs (the superposition
property).
• While the implications of linearity are far-reaching, the mathematical
definition is simple.
• Let us represent the general linear (but possibly time-varying) filter as
a signal operator:

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 84

 Linear Filtering

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 85

 Linear Filtering
• where S denotes the signal space (complex-valued sequences, in general).
• These two conditions are simply a mathematical restatement of the previous descriptive
definition.
• The scaling property of linear systems states that scaling the input of a linear system (multiplying
it by a constant gain factor) scales the output by the same factor.
• The superposition property of linear systems states that the response of a linear system to a sum
of signals is the sum of the responses to each individual input signal.
• Another view is that the individual signals which have been summed at the input are processed
independently inside the filter--they superimpose and do not interact.
• Another example of a linear signal medium is the earth's atmosphere.
• When two sounds are in the air at once, the air pressure fluctuations that convey them simply
add.
• Since any finite continuous signal can be represented as a sum (i.e., superposition) of sinusoids,
we can predict the filter response to any input signal just by knowing the response for
all sinusoids. Without superposition, we have no such general description and it may be
impossible to do any better than to catalog the filter output for each possible input. Linear
operators distribute over linear combinations, i.e.,
04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 86
 Linear Filtering

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 87

 Adaptive filters-General Structure

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 88

 Adaptive filters-General Structure

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 89

 LMS Adaptive Filter

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 90

 LMS Adaptive Filter

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 91

 LMS Adaptive Filter

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 92

 LMS Adaptive Filter

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 93

 LMS Adaptive Filter

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 94

 Noise Cancellation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 95

 Noise Cancellation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 96

 Noise Cancellation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 97

 Noise Cancellation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 98

 Noise Cancellation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 99

 Noise Cancellation

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 100

 Feature Extraction
• In real life, all the data we collect are in large amounts.
• To understand this data, we need a process.
• Manually, it is not possible to process them. Here’s when the concept
of feature extraction comes in.
• Suppose you want to work with some of the big machine learning
projects or the coolest and popular domains such as deep learning,
where you can use images to make a project on object detection.
• Making projects on computer vision where you can to work with
thousands of interesting project in the image data set.
• To work with them, you have to go for feature extraction procedure
which will make your life easy.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 101

 Feature Extraction

• Feature extraction is a part of the dimensionality reduction process, in

which, an initial set of the raw data is divided and reduced to more
manageable groups.
• So when you want to process it will be easier.
• The most important characteristic of these large data sets is that they have
a large number of variables.
• These variables require a lot of computing resources to process them. So
Feature extraction helps to get the best feature from those big data sets by
select and combine variables into features, thus, effectively reducing the
amount of data.
• These features are easy to process, but still able to describe the actual data
set with the accuracy and originality.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 102

 Why Feature Extraction is Useful?

• The technique of extracting the features is useful when you have a

large data set and need to reduce the number of resources without
losing any important or relevant information.
• Feature extraction helps to reduce the amount of redundant data
from the data set.
• In the end, the reduction of the data helps to build the model with
less machine’s efforts and also increase the speed of learning and
generalization steps in the machine learning process.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 103

 Applications of Feature Extraction
• Bag of Words- Bag-of-Words is the most used technique for natural language
processing. In this process they extract the words or the features from a
sentence, document, website, etc. and then they classify them into the frequency
of use. So in this whole process feature extraction is one of the most important
parts.
• Image Processing –Image processing is one of the best and most interesting
domain. In this domain basically you will start playing with your images in order
to understand them. So here we use many techniques which includes feature
extraction as well and algorithms to detect features such as shaped, edges, or
motion in a digital image or video to process them.
• Auto-encoders: The main purpose of the auto-encoders is efficient data coding
which is unsupervised in nature. this process comes under unsupervised
learning . So Feature extraction procedure is applicable here to identify the key
features from the data to code by learning from the coding of the original data
set to derive new ones.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 104

 Pattern Recognition
• One of the most common applications of machine learning is pattern
recognition.
• Computers that use well-trained algorithms recognize animals in
photos, anomalies in stock fluctuations, and signs of cancer in
mammograms much better than humans.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 105

 Pattern Recognition
• Pattern recognition is the process of recognizing regularities in data by a
machine that uses machine learning algorithms.
• In the heart of the process lies the classification of events based on
statistical information, historical data, or the machine’s memory.
• A pattern is a regularity in the world or in abstract notions.
• If we talk about books or movies, a description of a genre would be a
pattern.
• For the machine to search for patterns in data, it should be pre-
processed and converted into a form that a computer can understand.
• Then, the researcher can use classification, regression, or clustering
algorithms depending on the information available about the problem to
get valuable results:

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 106

 Pattern Recognition
• Classification. In classification, the algorithm assigns labels to data
based on the predefined features. This is an example of supervised
learning.
• Clustering. An algorithm splits data into a number of clusters based
on the similarity of features. This is an example of unsupervised
learning.
• Regression. Regression algorithms try to find a relationship between
variables and predict unknown dependent variables based on known
data. It is based on supervised learning.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 107

 What should a pattern recognition system be
able to do?
If we want to assess how good or bad a pattern recognition system is,
you need to pay attention to what it can do:
• Identify a familiar pattern quickly and accurately.
• Classify unfamiliar objects.
• Recognize shapes and objects from different angles.
• Uncover patterns and objects, even when partly hidden.
• Automatically recognize patterns.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 108

 PATTERN RECOGNITION AND IT’S TYPES-
• Pattern recognition is the scientific discipline that allows us to classify
objects into several categories or classes that can be further used to
perform analysis and improve certain things. The three best-known
approaches for pattern recognition are:
• 1) Template matching-Template Matching is used to determine the
similarity between two entities (points, curves, or shapes) of the
same type. The pattern to be recognized is matched with a stored
template along with geometrical transformations. This approach has
some obvious disadvantages of being too rigid and having the need
for lots of templates.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 109

 PATTERN RECOGNITION AND IT’S TYPES-
• 2) Statistical classification–In this method, each pattern is
represented in terms of some features or measurements. The main
objective of this approach is to establish decision boundaries in the
feature space. This separates patterns belonging to different classes
creating some rules for an inter-class boundary.
• 3) Syntactic or structural matching–This method works on a
hierarchy framework where a pattern is said to be composed of
simple sub-patterns that are themselves built from yet simpler sub-
patterns. Considered equivalent to languages where primitives are
alphabets which make words then lines than the page and then
documents.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 110

 STEPS INVOLVED IN PATTERN RECOGNITION-
The major steps involved in a typical pattern recognition process are-
• Collection of relevant data from various sources
• Pre-processing of data – It involves removing noise from data and
making data in a format suitable for applying algorithms.
• Examining data and Dividing into classes
• Analyzing of various classes and its boundaries
• Applying these analyses according to the needs.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 111

SOME USE CASES OF PATTERN RECOGNITION-
• Let’s understand some fascinating use cases of pattern recognition-
• Image Recognition – This refers to recognizing the image and describing what is present in the image. The
image is thus made comparable to other similar images. Image recognition has its use in Visual Search, Face
recognition and other biometric methods like iris matching, etc.
• OCR – Optical Character Recognition is one of the variations of Image Recognition which generally involves
scanning and analyzing documents and photographs consisting of alphanumeric text to convert it into
machine-encoded text. This generally matches the input text with the given library of patterns. OCR has its
use in handwriting recognition, license plate recognition, Document classification, and other awesome stuff.
• Natural Language Processing and Sentiment Analysis – Natural Language Processing focuses on teaching
machines to comprehend human language and generate their messages. NLP doesn’t deal with the
substance of communication (i.e., reading between the lines) – it only deals with what is directly expressed
in the message. Whereas Sentiment analysis tries to find the meaning and nature of the text. It tries to know
about the mood, opinion, and intent of the text. NLP can be used for plagiarism detector tools or text
correction tools whereas sentiment analysis is helpful for opinion mining, recommender systems, etc.
• Voice Recognition – Voice recognition systems involve analysis of audio signals to interpret words or phrases
from it. Voice recognition can be used for Personal Assistants, Speech-to-text- converters, etc.

04-01-2023 Sumana Chatterjee, Asst. Prof., BME, NSEC 112