PTCCS369 Text and Speech Analysis Syllabus:

PTCCS369 Text and Speech Analysis Syllabus – Anna University Part time Regulation 2023

COURSE OBJECTIVES:

 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

UNIT I NATURAL LANGUAGE BASICS

Foundations of natural language processing – Language Syntax and Structure- Text Preprocessing and Wrangling – Text tokenization – Stemming – Lemmatization – Removing stop-words – Feature Engineering for Text representation – Bag of Words model- Bag of N-Grams model – TF-IDF model
Suggested Activities
● Flipped classroom on NLP
● Implementation of Text Preprocessing using NLTK
● Implementation of TF-IDF models
Suggested Evaluation Methods
 Quiz on NLP Basics
 Demonstration of Programs

UNIT II TEXT CLASSIFICATION

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
Suggested Activities
 Flipped classroom on Feature extraction of documents
 Implementation of SVM models for text classification
 External learning: Text summarization and Topic models
Suggested Evaluation Methods
 Assignment on above topics
 Quiz on RNN, Transformers
 Implementing NLP with RNN and Transformers

UNIT III QUESTION ANSWERING AND DIALOGUE SYSTEMS

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
Suggested Activities:
 Flipped classroom on language models for QA
 Developing a knowledge-based question-answering system
 Classic QA model development
Suggested Evaluation Methods
 Assignment on the above topics
 Quiz on knowledge-based question answering system
 Development of simple chatbots

UNIT IV TEXT-TO-SPEECH SYNTHESIS

Overview. Text normalization. Letter-to-sound. Prosody, Evaluation. Signal processing – Concatenative and parametric approaches, WaveNet and other deep learning-based TTS systems
Suggested Activities:
 Flipped classroom on Speech signal processing
 Exploring Text normalization
 Data collection
 Implementation of TTS systems
Suggested Evaluation Methods
 Assignment on the above topics
 Quiz on wavenet, deep learning-based TTS systems
 Finding accuracy with different TTS systems

UNIT V AUTOMATIC SPEECH RECOGNITION

Speech recognition: Acoustic modelling – Feature Extraction – HMM, HMM-DNN systems
Suggested Activities:
 Flipped classroom on Speech recognition.
 Exploring Feature extraction
Suggested Evaluation Methods
 Assignment on the above topics
 Quiz on acoustic modelling

30 PERIODS
PRACTICAL EXERCISES 30 PERIODS

1. Create Regular expressions in Python for detecting word patterns and tokenizing text
2. Getting started with Python and NLTK – Searching Text, Counting Vocabulary, Frequency Distribution, Collocations, Bigrams
3. Accessing Text Corpora using NLTK in Python
4. Write a function that finds the 50 most frequently occurring words of a text that are not stop words.
5. Implement the Word2Vec model
6. Use a transformer for implementing classification
7. Design a chatbot with a simple dialog system
8. Convert text to speech and find accuracy
9. Design a speech recognition system and find the error rate

TOTAL: 60 PERIODS
COURSE OUTCOMES:

On completion of the course, the students will 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 modelling 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

TEXTBOOK

1. Daniel Jurafsky and James H. Martin, “Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition”, Third Edition, 2022.

REFERENCES:

1. Dipanjan Sarkar, “Text Analytics with Python: A Practical Real-World approach to Gaining Actionable insights from your data”, APress,2018.
2. Tanveer Siddiqui, Tiwary U S, “Natural Language Processing and Information Retrieval”, Oxford University Press, 2008.
3. Lawrence Rabiner, Biing-Hwang Juang, B. Yegnanarayana, “Fundamentals of Speech Recognition” 1st Edition, Pearson, 2009.
4. Steven Bird, Ewan Klein, and Edward Loper, “Natural language processing with Python”, O’REILLY.