SRI SHAKTHI INSTITUTE OF ENGINEERING AND TECHNOLOGY

L & T BYPASS ROAD, COIMBATORE – 641 062

LESSON PLAN

FACULTY NAME : [Link] R ACADEMIC YEAR : 2024-25

DEPARTMENT : AIML SEMESTER : IV
SUBJECT CODE : 21AM801 CREDITS :3
SUBJECT NAME : Text and Speech Analysis REGULATION : 2021
COURSE TYPE : REGULAR
COURSE PRE-REQUISITES
[Link] COURSE NAME DESCRIPTION SEM

-
- - -

Course Objective:
The course aims to provide the students
● Understand natural language processing basics
● Apply classification algorithms to text documents
● Build question-answering and dialogue systems
● Develop a speech recognition system
● Develop a speech synthesizer

Course Outcome:

At the end of the course students should be able to

CO1: Explain existing and emerging deep learning architectures for text and speech processing
CO2: Apply deep learning techniques for NLP tasks, language modeling and machine translation
CO3: Explain coreference and coherence for text processing
CO4: Build question-answering systems, chatbots and dialogue systems
CO5: Apply deep learning models for building speech recognition and text-to-speech systems
UNIT –I NATURAL LANGUAGE BASICS

Syllabus - Foundations of natural language processing – Language Syntax and Structure- Text Preprocessing and
Wrangling – Text tokenization – Stemming – Lemmatization – Removing stopwords – Feature
Engineering for Text representation – Bag of Words model- Bag of N-Grams model – TF-IDF model

Books No. of
Sessi Levels of
Referred Page Periods Teaching
on Topics to be Covered Instructional CO
(with No. required Methodology
No. Delivery
chapter) (45 min)
 Introduction to NLP, R1, Chapter 1 1-25 Lecture/Demo Understand 1
Language Syntax & &2
1 Structure, Importance, 1
and Applications

Text Preprocessing: R1, Chapter 3 26-40 Demonstration Understand 1

Cleaning, Normalization,
1
2 Lowercasing, Removing
Punctuation

Text Tokenization: R1, Chapter 4 41-55 Demonstration Apply 1

3 Types, Methods, and 1
Challenges

Stemming: Algorithms R1, Chapter 5 56-70 PPT Apply 2

4 1
(Porter, Snowball)

Lemmatization: R1, Chapter 6 71-85 Demo/Hands-on Apply 2

5 Techniques, Differences 1
with Stemming

Removing Stopwords & R1, Chapter 7 86-95 Lecture/ Apply 2

6 Importance in Text 1 Discussion
Preprocessing

Feature Engineering for R1, Chapter 8 96-110 Demo/Hands-on Apply 2

7 Text Representation: 1
Overview

Bag of Words Model: R1, Chapter 9 111-125 Demo/Practice Apply 3

8 1
Concept, Applications

Bag of N-Grams Model: R1, Chapter 10 126-140 Demo/Practice Apply 4

9 1
Working and Use Cases

TF-IDF Model: R1, Chapter 11 141-150 Lecture/Demo Understand 2

10 Introduction and Use in 1
Text Mining

Applications of NLP: 161-175 Demo/Practice Analyze 3

11 Text Classification and R1, Chapter 13 1
Sentiment Analysis

Introduction to Deep R2, Chapter 1 1-15 Lecture/Demo Understand 2

12 1
Learning Models for NLP

13 Speech Recognition and R3, Chapter 2 16-45 1 Analyze 3

Text-to-Speech Systems &3 Demo/Practice
 Real-World Applications R1, Chapter 14 176-200 Discussion/Q&A Analyze 5
14 of NLP: Case Studies and 1
Review

Total Periods: 14

UNIT II – TEXT CLASSIFICATION

Syllabus - Vector Semantics and Embeddings -Word Embeddings - Word2Vec model – Glove model – FastText
model – Overview of Deep Learning models – RNN – Transformers – Overview of Text summarization
and Topic Models

Books No. of
Sessi Levels of
Referred Page Periods Teaching
on Topics to be Covered Instructional CO
(with No. required Methodology
No. Delivery
chapter) (45 min)
15 Introduction to Vector R2, 2
Semantics,Word Chapter 1-45 Understand
1 Lecturing
Embeddings 6,7

16 Word2Vec, R1, Demo 3

GloVe,FastText Model: Chapter 21-130 1 Apply
8,9,10

17,18 Deep Learning Models in R2, Lecturing 5

NLP,RNN Chapter 1-70 2 Understand
1,2

19 Transformers,Text R1, Lecturing 6

Summarization Chapter 11 131-160 1 Analyze
Techniques:

20 Topic Models-LDA, and R1, Lecturing 6

applications in text Chapter 12 161-190 1 Apply
analysis.

Total Periods: 06

UNIT III - QUESTION ANSWERING AND DIALOGUE SYSTEMS

 Syllabus - Information retrieval – IR-based question answering – knowledge-based question answering – language
models for QA – classic QA models – chatbots – Design of dialogue systems -–evaluating dialogue
systems

Books No. of Levels of

Session Referred Page Periods Teaching Instructio
Topics to be Covered CO
No. (with No. required Methodology nal
chapter) (45 min) Delivery
Introduction to R1, Chapter 1 1-25 Lecture/Demo
21 1
Information Retrieval (IR): Understand 3

IR-based Question R1, Chapter 2 26-55 1 Lecture/Hands-on Apply 2

22
Answering:

Knowledge-based R2, Chapter 3 56-90 1 Lecture/Demo Understand 3

23
Question Answering:

24 Language Models for QA: R2, Chapter 4 91-130 1 Lecture/Hands-on Apply 6

Chatbots & Dialogue R1, Chapter 5 131-180 1 Lecture/Demo, Analyze 7

25
Systems: Discussion

26 Quiz - - 1 Activity Evaluate

3

Total Periods: 06

UNIT IV - TEXT-TO-SPEECH SYNTHESIS

Syllabus - Overview. Text normalization. Letter-to-sound. Prosody, Evaluation. Signal processing - Concatenative
and parametric approaches, WaveNet and other deep learning-based TTS systems

No. of
Sessi Books Periods Levels of
Page Teaching
on Topics to be Covered Referred (with require Instructional CO
No. Methodology
No. chapter) d (45 Delivery
min)
Overview of Text-to- R1, Chapter 1 1-25 Lecture/Demo Understand 1
27 Speech (TTS) Systems: 1

Text Normalization R1, Chapter 2 26-50 Demo Apply 2

28 1
Letter-to-Sound R1, Chapter 3 51-80 Lecture/Hands- Apply 3
29
Conversion: 1 on

30 Prosody and Evaluation R1, Chapter 4 81-120 1 PPT Apply 4

in TTS:
31 Signal Processing and R1, Chapter 5 121-160 1 Lecture/ Analyze 5
 Deep Learning-Based Discussion
TTS (WaveNet):

Total periods: 05

UNIT V AUTOMATIC SPEECH RECOGNITION

Syllabus - Speech recognition: Acoustic modelling – Feature Extraction - HMM, HMM-DNN systems

Books No. of
Sessi Levels of
Referred Page Periods Teaching C
on Topics to be Covered Instructional
(with No. required Methodology O
No. Delivery
chapter) (45 min)
Introduction to Speech R1, Chapter 1 Lecture/Demo Understand 2
Recognition: Overview of speech
32 1-25 1
recognition, its components, and
challenges.
Acoustic Modeling and Feature R1, Chapter 2 26-60 Lecture/Demo Apply 3
Extraction: Introduction to acoustic
33 models and feature extraction 1
techniques used in speech
recognition systems.
Hidden Markov Models (HMM) and R2, Chapter 3 61-100 Demonstration Apply 3
HMM-DNN Systems:
34 Understanding HMM-based speech
1
recognition systems and the
integration of deep neural
networks (DNNs).
35 2 ICT Create
Review 5

Total periods: 04

Mapping of Content Beyond Syllabus to Course Outcome, PO, PSO:

Content Beyond Course Outcome PO PSO

Syllabus Topics

Deep Research Agents 2 2 1,2

Description about Content Beyond Syllabus topics: (write in paragraphs)

This AI agent autonomously browses the web to generate cited reports on user-specified topics, saving significant time in research
tasks. It can interpret and analyze text, images, and PDFs, offering expert-level insights

TEXT BOOKS:
T1: Apply deep learning models for building speech recognition and text-to-speech systems
REFERENCE BOOKS:
R1: Dipanjan Sarkar, “Text Analytics with Python: A Practical Real-World approach to Gaining Actionable insights from your data”, APress,2018
R2: Tanveer Siddiqui, Tiwary U S, “Natural Language Processing and Information Retrieval”, Oxford University Press, 2008
R3: Lawrence Rabiner, Biing-Hwang Juang, B. Yegnanarayana, “Fundamentals of Speech Recognition” 1st Edition, Pearson, 2009
R4: Steven Bird, Ewan Klein, and Edward Loper, “Natural language processing with Python”,O’REILLY

Web Resources: 1. [Link]

Mapping of Course outcomes (COs) to Program outcomes (POs)

PO PO PO PO PO
PO1 PO2 PO4 PO5 PO10 PO11 PO12
3 6 7 8 9
CO1 3 3 3 3
CO2 3 2 3 3 3
CO3 3 3 3
CO4 3 3 3
CO5 3 2 3 3 3
CO6 3 2 3 3 3

1 - Low 2 – Medium 3- High

Mapping of Course outcomes (POs)to Program Specific outcomes(PSOs)

PSO1 PSO2 PSO3

CO1 3
CO2 3 3
CO3 3
CO4 3
CO5 3 3
CO6 3 3

Prepared By

Approved By
[Link].S